Yu Tsao

Yen-Ju Lu, Xuankai Chang, Chenda Li et al. · cmu

This paper presents recent progress on integrating speech separation and enhancement (SSE) into the ESPnet toolkit. Compared with the previous ESPnet-SE work, numerous features have been added, including recent state-of-the-art speech enhancement models with their respective training and evaluation recipes. Importantly, a new interface has been designed to flexibly combine speech enhancement front-ends with other tasks, including automatic speech recognition (ASR), speech translation (ST), and spoken language understanding (SLU). To showcase such integration, we performed experiments on carefully designed synthetic datasets for noisy-reverberant multi-channel ST and SLU tasks, which can be used as benchmark corpora for future research. In addition to these new tasks, we also use CHiME-4 and WSJ0-2Mix to benchmark multi- and single-channel SE approaches. Results show that the integration of SE front-ends with back-end tasks is a promising research direction even for tasks besides ASR, especially in the multi-channel scenario. The code is available online at https://github.com/ESPnet/ESPnet. The multi-channel ST and SLU datasets, which are another contribution of this work, are released on HuggingFace.

Yuan Tseng, Layne Berry, Yi-Ting Chen et al. · meta-ai, mit

Audio-visual representation learning aims to develop systems with human-like perception by utilizing correlation between auditory and visual information. However, current models often focus on a limited set of tasks, and generalization abilities of learned representations are unclear. To this end, we propose the AV-SUPERB benchmark that enables general-purpose evaluation of unimodal audio/visual and bimodal fusion representations on 7 datasets covering 5 audio-visual tasks in speech and audio processing. We evaluate 5 recent self-supervised models and show that none of these models generalize to all tasks, emphasizing the need for future study on improving universal model performance. In addition, we show that representations may be improved with intermediate-task fine-tuning and audio event classification with AudioSet serves as a strong intermediate task. We release our benchmark with evaluation code and a model submission platform to encourage further research in audio-visual learning.

Chao-Han Huck Yang, Taejin Park, Yuan Gong et al. · gatech

Given recent advances in generative AI technology, a key question is how large language models (LLMs) can enhance acoustic modeling tasks using text decoding results from a frozen, pretrained automatic speech recognition (ASR) model. To explore new capabilities in language modeling for speech processing, we introduce the generative speech transcription error correction (GenSEC) challenge. This challenge comprises three post-ASR language modeling tasks: (i) post-ASR transcription correction, (ii) speaker tagging, and (iii) emotion recognition. These tasks aim to emulate future LLM-based agents handling voice-based interfaces while remaining accessible to a broad audience by utilizing open pretrained language models or agent-based APIs. We also discuss insights from baseline evaluations, as well as lessons learned for designing future evaluations.

Chi-Chang Lee, Yu Tsao, Hsin-Min Wang et al.

The performance of acoustic models degrades notably in noisy environments. Speech enhancement (SE) can be used as a front-end strategy to aid automatic speech recognition (ASR) systems. However, existing training objectives of SE methods are not fully effective at integrating speech-text and noisy-clean paired data for training toward unseen ASR systems. In this study, we propose a general denoising framework, D4AM, for various downstream acoustic models. Our framework fine-tunes the SE model with the backward gradient according to a specific acoustic model and the corresponding classification objective. In addition, our method aims to consider the regression objective as an auxiliary loss to make the SE model generalize to other unseen acoustic models. To jointly train an SE unit with regression and classification objectives, D4AM uses an adjustment scheme to directly estimate suitable weighting coefficients rather than undergoing a grid search process with additional training costs. The adjustment scheme consists of two parts: gradient calibration and regression objective weighting. The experimental results show that D4AM can consistently and effectively provide improvements to various unseen acoustic models and outperforms other combination setups. Specifically, when evaluated on the Google ASR API with real noisy data completely unseen during SE training, D4AM achieves a relative WER reduction of 24.65% compared with the direct feeding of noisy input. To our knowledge, this is the first work that deploys an effective combination scheme of regression (denoising) and classification (ASR) objectives to derive a general pre-processor applicable to various unseen ASR systems. Our code is available at https://github.com/ChangLee0903/D4AM.

Szu-Wei Fu, Rong Chao, Xuesong Yang et al.

Universal Speech Enhancement (USE) aims to restore speech quality under diverse degradation conditions while preserving signal fidelity. Despite recent progress, key challenges in training target selection, the distortion--perception tradeoff, and data curation remain unresolved. In this work, we systematically address these three overlooked problems. First, we revisit the conventional practice of using early-reflected speech as the dereverberation target and show that it can degrade perceptual quality and downstream ASR performance. We instead demonstrate that time-shifted anechoic clean speech provides a superior learning target. Second, guided by the distortion--perception tradeoff theory, we propose a simple two-stage framework that achieves minimal distortion under a given level of perceptual quality. Third, we analyze the trade-off between training data scale and quality for USE, revealing that training on large uncurated corpora imposes a performance ceiling, as models struggle to remove subtle artifacts. Our method achieves state-of-the-art performance on the URGENT 2025 non-blind test set and exhibits strong language-agnostic generalization, making it effective for improving TTS training data. Model weights are available for download at: https://huggingface.co/nvidia/RE-USE.

Ryandhimas E. Zezario, Fei Chen, Chiou-Shann Fuh et al.

Improving the user's hearing ability to understand speech in noisy environments is critical to the development of hearing aid (HA) devices. For this, it is important to derive a metric that can fairly predict speech intelligibility for HA users. A straightforward approach is to conduct a subjective listening test and use the test results as an evaluation metric. However, conducting large-scale listening tests is time-consuming and expensive. Therefore, several evaluation metrics were derived as surrogates for subjective listening test results. In this study, we propose a multi-branched speech intelligibility prediction model (MBI-Net), for predicting the subjective intelligibility scores of HA users. MBI-Net consists of two branches of models, with each branch consisting of a hearing loss model, a cross-domain feature extraction module, and a speech intelligibility prediction model, to process speech signals from one channel. The outputs of the two branches are fused through a linear layer to obtain predicted speech intelligibility scores. Experimental results confirm the effectiveness of MBI-Net, which produces higher prediction scores than the baseline system in Track 1 and Track 2 on the Clarity Prediction Challenge 2022 dataset.

Tsun-An Hsieh, Chao-Han Huck Yang, Pin-Yu Chen et al. · gatech, nvidia

This study addresses the speech enhancement (SE) task within the causal inference paradigm by modeling the noise presence as an intervention. Based on the potential outcome framework, the proposed causal inference-based speech enhancement (CISE) separates clean and noisy frames in an intervened noisy speech using a noise detector and assigns both sets of frames to two mask-based enhancement modules (EMs) to perform noise-conditional SE. Specifically, we use the presence of noise as guidance for EM selection during training, and the noise detector selects the enhancement module according to the prediction of the presence of noise for each frame. Moreover, we derived a SE-specific average treatment effect to quantify the causal effect adequately. Experimental evidence demonstrates that CISE outperforms a non-causal mask-based SE approach in the studied settings and has better performance and efficiency than more complex SE models.

Ryandhimas E. Zezario, Dyah A. M. G. Wisnu, Szu-Wei Fu et al. · gatech

In this paper, we introduce GatherMOS, a novel framework that leverages large language models (LLM) as meta-evaluators to aggregate diverse signals into quality predictions. GatherMOS integrates lightweight acoustic descriptors with pseudo-labels from DNSMOS and VQScore, enabling the LLM to reason over heterogeneous inputs and infer perceptual mean opinion scores (MOS). We further explore both zero-shot and few-shot in-context learning setups, showing that zero-shot GatherMOS maintains stable performance across diverse conditions, while few-shot guidance yields large gains when support samples match the test conditions. Experiments on the VoiceBank-DEMAND dataset demonstrate that GatherMOS consistently outperforms DNSMOS, VQScore, naive score averaging, and even learning-based models such as CNN-BLSTM and MOS-SSL when trained under limited labeled-data conditions. These results highlight the potential of LLM-based aggregation as a practical strategy for non-intrusive speech quality evaluation.

Ryandhimas E. Zezario, Szu-wei Fu, Fei Chen et al.

Recently, deep learning (DL)-based non-intrusive speech assessment models have attracted great attention. Many studies report that these DL-based models yield satisfactory assessment performance and good flexibility, but their performance in unseen environments remains a challenge. Furthermore, compared to quality scores, fewer studies elaborate deep learning models to estimate intelligibility scores. This study proposes a multi-task speech intelligibility prediction model, called MTI-Net, for simultaneously predicting human and machine intelligibility measures. Specifically, given a speech utterance, MTI-Net is designed to predict human subjective listening test results and word error rate (WER) scores. We also investigate several methods that can improve the prediction performance of MTI-Net. First, we compare different features (including low-level features and embeddings from self-supervised learning (SSL) models) and prediction targets of MTI-Net. Second, we explore the effect of transfer learning and multi-tasking learning on training MTI-Net. Finally, we examine the potential advantages of fine-tuning SSL embeddings. Experimental results demonstrate the effectiveness of using cross-domain features, multi-task learning, and fine-tuning SSL embeddings. Furthermore, it is confirmed that the intelligibility and WER scores predicted by MTI-Net are highly correlated with the ground-truth scores.

Yu Tsao, Hao-Chun Chu, Shih-Wei Lan et al.

This paper proposes a deep cerebellar model articulation controller (DCMAC) for adaptive noise cancellation (ANC). We expand upon the conventional CMAC by stacking sin-gle-layer CMAC models into multiple layers to form a DCMAC model and derive a modified backpropagation training algorithm to learn the DCMAC parameters. Com-pared with conventional CMAC, the DCMAC can characterize nonlinear transformations more effectively because of its deep structure. Experimental results confirm that the pro-posed DCMAC model outperforms the CMAC in terms of residual noise in an ANC task, showing that DCMAC provides enhanced modeling capability based on channel characteristics.

Hung-Shin Lee, Yu Tsao, Shyh-Kang Jeng et al.

Phonotactic constraints can be employed to distinguish languages by representing a speech utterance as a multinomial distribution or phone events. In the present study, we propose a new learning mechanism based on subspace-based representation, which can extract concealed phonotactic structures from utterances, for language verification and dialect/accent identification. The framework mainly involves two successive parts. The first part involves subspace construction. Specifically, it decodes each utterance into a sequence of vectors filled with phone-posteriors and transforms the vector sequence into a linear orthogonal subspace based on low-rank matrix factorization or dynamic linear modeling. The second part involves subspace learning based on kernel machines, such as support vector machines and the newly developed subspace-based neural networks (SNNs). The input layer of SNNs is specifically designed for the sample represented by subspaces. The topology ensures that the same output can be derived from identical subspaces by modifying the conventional feed-forward pass to fit the mathematical definition of subspace similarity. Evaluated on the "General LR" test of NIST LRE 2007, the proposed method achieved up to 52%, 46%, 56%, and 27% relative reductions in equal error rates over the sequence-based PPR-LM, PPR-VSM, and PPR-IVEC methods and the lattice-based PPR-LM method, respectively. Furthermore, on the dialect/accent identification task of NIST LRE 2009, the SNN-based system performed better than the aforementioned four baseline methods.

Chan-Jan Hsu, Ho-Lam Chung, Hung-yi Lee et al.

In Spoken language understanding (SLU), a natural solution is concatenating pre-trained speech models (e.g. HuBERT) and pretrained language models (PLM, e.g. T5). Most previous works use pretrained language models with subword-based tokenization. However, the granularity of input units affects the alignment of speech model outputs and language model inputs, and PLM with character-based tokenization is underexplored. In this work, we conduct extensive studies on how PLMs with different tokenization strategies affect spoken language understanding task including spoken question answering (SQA) and speech translation (ST). We further extend the idea to create T5lephone(pronounced as telephone), a variant of T5 that is pretrained using phonemicized text. We initialize T5lephone with existing PLMs to pretrain it using relatively lightweight computational resources. We reached state-of-the-art on NMSQA, and the T5lephone model exceeds T5 with other types of units on end-to-end SQA and ST.

Li-Chin Chen, Po-Hsun Chen, Richard Tzong-Han Tsai et al.

Speech generation and enhancement based on articulatory movements facilitate communication when the scope of verbal communication is absent, e.g., in patients who have lost the ability to speak. Although various techniques have been proposed to this end, electropalatography (EPG), which is a monitoring technique that records contact between the tongue and hard palate during speech, has not been adequately explored. Herein, we propose a novel multimodal EPG-to-speech (EPG2S) system that utilizes EPG and speech signals for speech generation and enhancement. Different fusion strategies based on multiple combinations of EPG and noisy speech signals are examined, and the viability of the proposed method is investigated. Experimental results indicate that EPG2S achieves desirable speech generation outcomes based solely on EPG signals. Further, the addition of noisy speech signals is observed to improve quality and intelligibility. Additionally, EPG2S is observed to achieve high-quality speech enhancement based solely on audio signals, with the addition of EPG signals further improving the performance. The late fusion strategy is deemed to be the most effective approach for simultaneous speech generation and enhancement.

Chan-Jan Hsu, Hung-yi Lee, Yu Tsao

Transformer-based models are widely used in natural language understanding (NLU) tasks, and multimodal transformers have been effective in visual-language tasks. This study explores distilling visual information from pretrained multimodal transformers to pretrained language encoders. Our framework is inspired by cross-modal encoders' success in visual-language tasks while we alter the learning objective to cater to the language-heavy characteristics of NLU. After training with a small number of extra adapting steps and finetuned, the proposed XDBERT (cross-modal distilled BERT) outperforms pretrained-BERT in general language understanding evaluation (GLUE), situations with adversarial generations (SWAG) benchmarks, and readability benchmarks. We analyze the performance of XDBERT on GLUE to show that the improvement is likely visually grounded.

Ryandhimas E. Zezario, Fei Chen, Chiou-Shann Fuh et al.

Automated speech intelligibility assessment is pivotal for hearing aid (HA) development. In this paper, we present three novel methods to improve intelligibility prediction accuracy and introduce MBI-Net+, an enhanced version of MBI-Net, the top-performing system in the 1st Clarity Prediction Challenge. MBI-Net+ leverages Whisper's embeddings to create cross-domain acoustic features and includes metadata from speech signals by using a classifier that distinguishes different enhancement methods. Furthermore, MBI-Net+ integrates the hearing-aid speech perception index (HASPI) as a supplementary metric into the objective function to further boost prediction performance. Experimental results demonstrate that MBI-Net+ surpasses several intrusive baseline systems and MBI-Net on the Clarity Prediction Challenge 2023 dataset, validating the effectiveness of incorporating Whisper embeddings, speech metadata, and related complementary metrics to improve prediction performance for HA.

Li-Wei Chen, Yao-Fei Cheng, Hung-Shin Lee et al.

The lack of clean speech is a practical challenge to the development of speech enhancement systems, which means that there is an inevitable mismatch between their training criterion and evaluation metric. In response to this unfavorable situation, we propose a training and inference strategy that additionally uses enhanced speech as a target by improving the previously proposed noisy-target training (NyTT). Because homogeneity between in-domain noise and extraneous noise is the key to the effectiveness of NyTT, we train various student models by remixing 1) the teacher model's estimated speech and noise for enhanced-target training or 2) raw noisy speech and the teacher model's estimated noise for noisy-target training. Experimental results show that our proposed method outperforms several baselines, especially with the teacher/student inference, where predicted clean speech is derived successively through the teacher and final student models.

Chiang-Lin Tai, Hung-Shin Lee, Yu Tsao et al.

Children speech recognition is indispensable but challenging due to the diversity of children's speech. In this paper, we propose a filter-based discriminative autoencoder for acoustic modeling. To filter out the influence of various speaker types and pitches, auxiliary information of the speaker and pitch features is input into the encoder together with the acoustic features to generate phonetic embeddings. In the training phase, the decoder uses the auxiliary information and the phonetic embedding extracted by the encoder to reconstruct the input acoustic features. The autoencoder is trained by simultaneously minimizing the ASR loss and feature reconstruction error. The framework can make the phonetic embedding purer, resulting in more accurate senone (triphone-state) scores. Evaluated on the test set of the CMU Kids corpus, our system achieves a 7.8% relative WER reduction compared to the baseline system. In the domain adaptation experiment, our system also outperforms the baseline system on the British-accent PF-STAR task.

Fan-Lin Wang, Yao-Fei Cheng, Hung-Shin Lee et al.

Recording channel mismatch between training and testing conditions has been shown to be a serious problem for speech separation. This situation greatly reduces the separation performance, and cannot meet the requirement of daily use. In this study, inheriting the use of our previously constructed TAT-2mix corpus, we address the channel mismatch problem by proposing a channel-aware audio separation network (CasNet), a deep learning framework for end-to-end time-domain speech separation. CasNet is implemented on top of TasNet. Channel embedding (characterizing channel information in a mixture of multiple utterances) generated by Channel Encoder is introduced into the separation module by the FiLM technique. Through two training strategies, we explore two roles that channel embedding may play: 1) a real-life noise disturbance, making the model more robust, or 2) a guide, instructing the separation model to retain the desired channel information. Experimental results on TAT-2mix show that CasNet trained with both training strategies outperforms the TasNet baseline, which does not use channel embeddings.

Chi-Chang Lee, Cheng-Hung Hu, Yu-Chen Lin et al.

For deep learning-based speech enhancement (SE) systems, the training-test acoustic mismatch can cause notable performance degradation. To address the mismatch issue, numerous noise adaptation strategies have been derived. In this paper, we propose a novel method, called noise adaptive speech enhancement with target-conditional resampling (NASTAR), which reduces mismatches with only one sample (one-shot) of noisy speech in the target environment. NASTAR uses a feedback mechanism to simulate adaptive training data via a noise extractor and a retrieval model. The noise extractor estimates the target noise from the noisy speech, called pseudo-noise. The noise retrieval model retrieves relevant noise samples from a pool of noise signals according to the noisy speech, called relevant-cohort. The pseudo-noise and the relevant-cohort set are jointly sampled and mixed with the source speech corpus to prepare simulated training data for noise adaptation. Experimental results show that NASTAR can effectively use one noisy speech sample to adapt an SE model to a target condition. Moreover, both the noise extractor and the noise retrieval model contribute to model adaptation. To our best knowledge, NASTAR is the first work to perform one-shot noise adaptation through noise extraction and retrieval.

Hung-Shin Lee, Pin-Yuan Chen, Yao-Fei Cheng et al.

Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability. In this paper, a noise-aware training framework based on two cascaded neural structures is proposed to jointly optimize speech enhancement and speech recognition. The feature enhancement module is composed of a multi-task autoencoder, where noisy speech is decomposed into clean speech and noise. By concatenating its enhanced, noise-aware, and noisy features for each frame, the acoustic-modeling module maps each feature-augmented frame into a triphone state by optimizing the lattice-free maximum mutual information and cross entropy between the predicted and actual state sequences. On top of the factorized time delay neural network (TDNN-F) and its convolutional variant (CNN-TDNNF), both with SpecAug, the two proposed systems achieve word error rate (WER) of 3.90% and 3.55%, respectively, on the Aurora-4 task. Compared with the best existing systems that use bigram and trigram language models for decoding, the proposed CNN-TDNNF-based system achieves a relative WER reduction of 15.20% and 33.53%, respectively. In addition, the proposed CNN-TDNNF-based system also outperforms the baseline CNN-TDNNF system on the AMI task.

Tin-Han Chi, Kai-Chun Liu, Chia-Yeh Hsieh et al.

Fall accidents are critical issues in an aging and aged society. Recently, many researchers developed pre-impact fall detection systems using deep learning to support wearable-based fall protection systems for preventing severe injuries. However, most works only employed simple neural network models instead of complex models considering the usability in resource-constrained mobile devices and strict latency requirements. In this work, we propose a novel pre-impact fall detection via CNN-ViT knowledge distillation, namely PreFallKD, to strike a balance between detection performance and computational complexity. The proposed PreFallKD transfers the detection knowledge from the pre-trained teacher model (vision transformer) to the student model (lightweight convolutional neural networks). Additionally, we apply data augmentation techniques to tackle issues of data imbalance. We conduct the experiment on the KFall public dataset and compare PreFallKD with other state-of-the-art models. The experiment results show that PreFallKD could boost the student model during the testing phase and achieves reliable F1-score (92.66%) and lead time (551.3 ms).

Li-Chin Chen, Kuo-Hsuan Hung, Yi-Ju Tseng et al.

The inherent nature of patient data poses several challenges. Prevalent cases amass substantial longitudinal data owing to their patient volume and consistent follow-ups, however, longitudinal laboratory data are renowned for their irregularity, temporality, absenteeism, and sparsity; In contrast, recruitment for rare or specific cases is often constrained due to their limited patient size and episodic observations. This study employed self-supervised learning (SSL) to pretrain a generalized laboratory progress (GLP) model that captures the overall progression of six common laboratory markers in prevalent cardiovascular cases, with the intention of transferring this knowledge to aid in the detection of specific cardiovascular event. GLP implemented a two-stage training approach, leveraging the information embedded within interpolated data and amplify the performance of SSL. After GLP pretraining, it is transferred for TVR detection. The proposed two-stage training improved the performance of pure SSL, and the transferability of GLP exhibited distinctiveness. After GLP processing, the classification exhibited a notable enhancement, with averaged accuracy rising from 0.63 to 0.90. All evaluated metrics demonstrated substantial superiority (p < 0.01) compared to prior GLP processing. Our study effectively engages in translational engineering by transferring patient progression of cardiovascular laboratory parameters from one patient group to another, transcending the limitations of data availability. The transferability of disease progression optimized the strategies of examinations and treatments, and improves patient prognosis while using commonly available laboratory parameters. The potential for expanding this approach to encompass other diseases holds great promise.

Yu-Wen Chen, Hsin-Min Wang, Yu Tsao

The performance of speech-processing models is heavily influenced by the speech corpus that is used for training and evaluation. In this study, we propose BAlanced Script PROducer (BASPRO) system, which can automatically construct a phonetically balanced and rich set of Chinese sentences for collecting Mandarin Chinese speech data. First, we used pretrained natural language processing systems to extract ten-character candidate sentences from a large corpus of Chinese news texts. Then, we applied a genetic algorithm-based method to select 20 phonetically balanced sentence sets, each containing 20 sentences, from the candidate sentences. Using BASPRO, we obtained a recording script called TMNews, which contains 400 ten-character sentences. TMNews covers 84% of the syllables used in the real world. Moreover, the syllable distribution has 0.96 cosine similarity to the real-world syllable distribution. We converted the script into a speech corpus using two text-to-speech systems. Using the designed speech corpus, we tested the performances of speech enhancement (SE) and automatic speech recognition (ASR), which are one of the most important regression- and classification-based speech processing tasks, respectively. The experimental results show that the SE and ASR models trained on the designed speech corpus outperform their counterparts trained on a randomly composed speech corpus.

Ryandhimas E. Zezario, Bo-Ren Brian Bai, Chiou-Shann Fuh et al.

This study proposes a multi-task pseudo-label learning (MPL)-based non-intrusive speech quality assessment model called MTQ-Net. MPL consists of two stages: obtaining pseudo-label scores from a pretrained model and performing multi-task learning. The 3QUEST metrics, namely Speech-MOS (S-MOS), Noise-MOS (N-MOS), and General-MOS (G-MOS), are the assessment targets. The pretrained MOSA-Net model is utilized to estimate three pseudo labels: perceptual evaluation of speech quality (PESQ), short-time objective intelligibility (STOI), and speech distortion index (SDI). Multi-task learning is then employed to train MTQ-Net by combining a supervised loss (derived from the difference between the estimated score and the ground-truth label) and a semi-supervised loss (derived from the difference between the estimated score and the pseudo label), where the Huber loss is employed as the loss function. Experimental results first demonstrate the advantages of MPL compared to training a model from scratch and using a direct knowledge transfer mechanism. Second, the benefit of the Huber loss for improving the predictive ability of MTQ-Net is verified. Finally, the MTQ-Net with the MPL approach exhibits higher overall predictive power compared to other SSL-based speech assessment models.

Ammarah Hashmi, Sahibzada Adil Shahzad, Chia-Wen Lin et al.

The recent proliferation of hyper-realistic deepfake videos has drawn attention to the threat of audio and visual forgeries. Most previous studies on detecting artificial intelligence-generated fake videos only utilize visual modality or audio modality. While some methods exploit audio and visual modalities to detect forged videos, they have not been comprehensively evaluated on multimodal datasets of deepfake videos involving acoustic and visual manipulations, and are mostly based on convolutional neural networks with low detection accuracy. Considering that human cognition instinctively integrates multisensory information including audio and visual cues to perceive and interpret content and the success of transformer in various fields, this study introduces the audio-visual transformer-based ensemble network (AVTENet). This innovative framework tackles the complexities of deepfake technology by integrating both acoustic and visual manipulations to enhance the accuracy of video forgery detection. Specifically, the proposed model integrates several purely transformer-based variants that capture video, audio, and audio-visual salient cues to reach a consensus in prediction. For evaluation, we use the recently released benchmark multimodal audio-video FakeAVCeleb dataset. For a detailed analysis, we evaluate AVTENet, its variants, and several existing methods on multiple test sets of the FakeAVCeleb dataset. Experimental results show that the proposed model outperforms all existing methods and achieves state-of-the-art performance on Testset-I and Testset-II of the FakeAVCeleb dataset. We also compare AVTENet against humans in detecting video forgery. The results show that AVTENet significantly outperforms humans.

Chien-Pin Liu, Ju-Hsuan Li, En-Ping Chu et al.

Falls are the public health issue for the elderly all over the world since the fall-induced injuries are associated with a large amount of healthcare cost. Falls can cause serious injuries, even leading to death if the elderly suffers a "long-lie". Hence, a reliable fall detection (FD) system is required to provide an emergency alarm for first aid. Due to the advances in wearable device technology and artificial intelligence, some fall detection systems have been developed using machine learning and deep learning methods to analyze the signal collected from accelerometer and gyroscopes. In order to achieve better fall detection performance, an ensemble model that combines a coarse-fine convolutional neural network and gated recurrent unit is proposed in this study. The parallel structure design used in this model restores the different grains of spatial characteristics and capture temporal dependencies for feature representation. This study applies the FallAllD public dataset to validate the reliability of the proposed model, which achieves a recall, precision, and F-score of 92.54%, 96.13%, and 94.26%, respectively. The results demonstrate the reliability of the proposed ensemble model in discriminating falls from daily living activities and its superior performance compared to the state-of-the-art convolutional neural network long short-term memory (CNN-LSTM) for FD.

Kuan-Chen Wang, Kai-Chun Liu, Sheng-Yu Peng et al.

Electrocardiogram (ECG) artifact contamination often occurs in surface electromyography (sEMG) applications when the measured muscles are in proximity to the heart. Previous studies have developed and proposed various methods, such as high-pass filtering, template subtraction and so forth. However, these methods remain limited by the requirement of reference signals and distortion of original sEMG. This study proposed a novel denoising method to eliminate ECG artifacts from the single-channel sEMG signals using fully convolutional networks (FCN). The proposed method adopts a denoise autoencoder structure and powerful nonlinear mapping capability of neural networks for sEMG denoising. We compared the proposed approach with conventional approaches, including high-pass filters and template subtraction, on open datasets called the Non-Invasive Adaptive Prosthetics database and MIT-BIH normal sinus rhythm database. The experimental results demonstrate that the FCN outperforms conventional methods in sEMG reconstruction quality under a wide range of signal-to-noise ratio inputs.

Chi-Chang Lee, Hong-Wei Chen, Chu-Song Chen et al.

The performance of speaker verification (SV) models may drop dramatically in noisy environments. A speech enhancement (SE) module can be used as a front-end strategy. However, existing SE methods may fail to bring performance improvements to downstream SV systems due to artifacts in the predicted signals of SE models. To compensate for artifacts, we propose a generic denoising framework named LC4SV, which can serve as a pre-processor for various unknown downstream SV models. In LC4SV, we employ a learning-based interpolation agent to automatically generate the appropriate coefficients between the enhanced signal and its noisy input to improve SV performance in noisy environments. Our experimental results demonstrate that LC4SV consistently improves the performance of various unseen SV systems. To the best of our knowledge, this work is the first attempt to develop a learning-based interpolation scheme aiming at improving SV performance in noisy environments.

Li-Chin Chen, Jung-Nien Lai, Hung-En Lin et al.

Low back pain (LBP) and sciatica may require surgical therapy when they are symptomatic of severe pain. However, there is no effective measures to evaluate the surgical outcomes in advance. This work combined elements of Eastern medicine and machine learning, and developed a preoperative assessment tool to predict the prognosis of lumbar spinal surgery in LBP and sciatica patients. Standard operative assessments, traditional Chinese medicine body constitution assessments, planned surgical approach, and vowel pronunciation recordings were collected and stored in different modalities. Our work provides insights into leveraging modality combinations, multimodals, and fusion strategies. The interpretability of models and correlations between modalities were also inspected. Based on the recruited 105 patients, we found that combining standard operative assessments, body constitution assessments, and planned surgical approach achieved the best performance in 0.81 accuracy. Our approach is effective and can be widely applied in general practice due to simplicity and effective.

Huan-Hsin Tseng, Hsin-Yi Lin, Kuo-Hsuan Hung et al.

Transfer learning is known to perform efficiently in many applications empirically, yet limited literature reports the mechanism behind the scene. This study establishes both formal derivations and heuristic analysis to formulate the theory of transfer learning in deep learning. Our framework utilizing layer variational analysis proves that the success of transfer learning can be guaranteed with corresponding data conditions. Moreover, our theoretical calculation yields intuitive interpretations towards the knowledge transfer process. Subsequently, an alternative method for network-based transfer learning is derived. The method shows an increase in efficiency and accuracy for domain adaptation. It is particularly advantageous when new domain data is sufficiently sparse during adaptation. Numerical experiments over diverse tasks validated our theory and verified that our analytic expression achieved better performance in domain adaptation than the gradient descent method.

Hsin-Yi Lin, Huan-Hsin Tseng, Yu Tsao

It has been shown recently that deep learning based models are effective on speech quality prediction and could outperform traditional metrics in various perspectives. Although network models have potential to be a surrogate for complex human hearing perception, they may contain instabilities in predictions. This work shows that deep speech quality predictors can be vulnerable to adversarial perturbations, where the prediction can be changed drastically by unnoticeable perturbations as small as $-30$ dB compared with speech inputs. In addition to exposing the vulnerability of deep speech quality predictors, we further explore and confirm the viability of adversarial training for strengthening robustness of models.

Sahibzada Adil Shahzad, Ammarah Hashmi, Yan-Tsung Peng et al.

Multimodal manipulations (also known as audio-visual deepfakes) make it difficult for unimodal deepfake detectors to detect forgeries in multimedia content. To avoid the spread of false propaganda and fake news, timely detection is crucial. The damage to either modality (i.e., visual or audio) can only be discovered through multimodal models that can exploit both pieces of information simultaneously. However, previous methods mainly adopt unimodal video forensics and use supervised pre-training for forgery detection. This study proposes a new method based on a multimodal self-supervised-learning (SSL) feature extractor to exploit inconsistency between audio and visual modalities for multimodal video forgery detection. We use the transformer-based SSL pre-trained Audio-Visual HuBERT (AV-HuBERT) model as a visual and acoustic feature extractor and a multi-scale temporal convolutional neural network to capture the temporal correlation between the audio and visual modalities. Since AV-HuBERT only extracts visual features from the lip region, we also adopt another transformer-based video model to exploit facial features and capture spatial and temporal artifacts caused during the deepfake generation process. Experimental results show that our model outperforms all existing models and achieves new state-of-the-art performance on the FakeAVCeleb and DeepfakeTIMIT datasets.

Kuo-Hsuan Hung, Kuan-Chen Wang, Kai-Chun Liu et al.

Electrocardiogram (ECG) is an important non-invasive method for diagnosing cardiovascular disease. However, ECG signals are susceptible to noise contamination, such as electrical interference or signal wandering, which reduces diagnostic accuracy. Various ECG denoising methods have been proposed, but most existing methods yield suboptimal performance under very noisy conditions or require several steps during inference, leading to latency during online processing. In this paper, we propose a novel ECG denoising model, namely Mamba-based ECG Enhancer (MECG-E), which leverages the Mamba architecture known for its fast inference and outstanding nonlinear mapping capabilities. Experimental results indicate that MECG-E surpasses several well-known existing models across multiple metrics under different noise conditions. Additionally, MECG-E requires less inference time than state-of-the-art diffusion-based ECG denoisers, demonstrating the model's functionality and efficiency.

Ke-Han Lu, Szu-Wei Fu, Chao-Han Huck Yang et al.

Large language models (LLMs) have been widely used as knowledge backbones of Large Audio Language Models (LALMs), yet how much auditory knowledge they encode through text-only pre-training and how this affects downstream performance remains unclear. We study this gap by comparing different LLMs under two text-only and one audio-grounded setting: (1) direct probing on AKB-2000, a curated benchmark testing the breadth and depth of auditory knowledge; (2) cascade evaluation, where LLMs reason over text descriptions from an audio captioner; and (3) audio-grounded evaluation, where each LLM is fine-tuned into a Large Audio Language Model (LALM) with an audio encoder. Our findings reveal that auditory knowledge varies substantially across families, and text-only results are strongly correlated with audio performance. Our work provides empirical grounding for a comprehensive understanding of LLMs in audio research.

Xugang Lu, Peng Shen, Yu Tsao et al.

Transferring linguistic knowledge from a pretrained language model (PLM) to an acoustic model has been shown to greatly improve the performance of automatic speech recognition (ASR). However, due to the heterogeneous feature distributions in cross-modalities, designing an effective model for feature alignment and knowledge transfer between linguistic and acoustic sequences remains a challenging task. Optimal transport (OT), which efficiently measures probability distribution discrepancies, holds great potential for aligning and transferring knowledge between acoustic and linguistic modalities. Nonetheless, the original OT treats acoustic and linguistic feature sequences as two unordered sets in alignment and neglects temporal order information during OT coupling estimation. Consequently, a time-consuming pretraining stage is required to learn a good alignment between the acoustic and linguistic representations. In this paper, we propose a Temporal Order Preserved OT (TOT)-based Cross-modal Alignment and Knowledge Transfer (CAKT) (TOT-CAKT) for ASR. In the TOT-CAKT, local neighboring frames of acoustic sequences are smoothly mapped to neighboring regions of linguistic sequences, preserving their temporal order relationship in feature alignment and matching. With the TOT-CAKT model framework, we conduct Mandarin ASR experiments with a pretrained Chinese PLM for linguistic knowledge transfer. Our results demonstrate that the proposed TOT-CAKT significantly improves ASR performance compared to several state-of-the-art models employing linguistic knowledge transfer, and addresses the weaknesses of the original OT-based method in sequential feature alignment for ASR.

Kai-Wei Chang, Yi-Cheng Lin, Huang-Cheng Chou et al.

Speech technologies have advanced rapidly and serve diverse populations worldwide. However, many languages remain underrepresented due to limited resources. In this paper, we introduce \textbf{TaigiSpeech}, a real-world speech intent dataset in Taiwanese Taigi (aka Taiwanese Hokkien/Southern Min), which is a low-resource and primarily spoken language. The dataset is collected from older adults, comprising 21 speakers with a total of 3k utterances. It is designed for practical intent detection scenarios, including healthcare and home assistant applications. To address the scarcity of labeled data, we explore two data mining strategies with two levels of supervision: keyword match data mining with LLM pseudo labeling via an intermediate language and an audio-visual framework that leverages multimodal cues with minimal textual supervision. This design enables scalable dataset construction for low-resource and unwritten spoken languages. TaigiSpeech will be released under the CC BY 4.0 license to facilitate broad adoption and research on low-resource and unwritten languages. The project website and the dataset can be found on https://kwchang.org/taigispeech.

Siyin Wang, Wenyi Yu, Xianzhao Chen et al.

This paper explores a novel perspective to speech quality assessment by leveraging natural language descriptions, offering richer, more nuanced insights than traditional numerical scoring methods. Natural language feedback provides instructive recommendations and detailed evaluations, yet existing datasets lack the comprehensive annotations needed for this approach. To bridge this gap, we introduce QualiSpeech, a comprehensive low-level speech quality assessment dataset encompassing 11 key aspects and detailed natural language comments that include reasoning and contextual insights. Additionally, we propose the QualiSpeech Benchmark to evaluate the low-level speech understanding capabilities of auditory large language models (LLMs). Experimental results demonstrate that finetuned auditory LLMs can reliably generate detailed descriptions of noise and distortion, effectively identifying their types and temporal characteristics. The results further highlight the potential for incorporating reasoning to enhance the accuracy and reliability of quality assessments. The dataset will be released at https://huggingface.co/datasets/tsinghua-ee/QualiSpeech.

Yu-Tung Liu, Kuan-Chen Wang, Kai-Chun Liu et al.

Surface electromyography (sEMG) recordings can be influenced by electrocardiogram (ECG) signals when the muscle being monitored is close to the heart. Several existing methods use signal-processing-based approaches, such as high-pass filter and template subtraction, while some derive mapping functions to restore clean sEMG signals from noisy sEMG (sEMG with ECG interference). Recently, the score-based diffusion model, a renowned generative model, has been introduced to generate high-quality and accurate samples with noisy input data. In this study, we proposed a novel approach, termed SDEMG, as a score-based diffusion model for sEMG signal denoising. To evaluate the proposed SDEMG approach, we conduct experiments to reduce noise in sEMG signals, employing data from an openly accessible source, the Non-Invasive Adaptive Prosthetics database, along with ECG signals from the MIT-BIH Normal Sinus Rhythm Database. The experiment result indicates that SDEMG outperformed comparative methods and produced high-quality sEMG samples. The source code of SDEMG the framework is available at: https://github.com/tonyliu0910/SDEMG

Pin-Yen Huang, Szu-Wei Fu, Yu Tsao

State-of-the-art (SOTA) semi-supervised learning techniques, such as FixMatch and it's variants, have demonstrated impressive performance in classification tasks. However, these methods are not directly applicable to regression tasks. In this paper, we present RankUp, a simple yet effective approach that adapts existing semi-supervised classification techniques to enhance the performance of regression tasks. RankUp achieves this by converting the original regression task into a ranking problem and training it concurrently with the original regression objective. This auxiliary ranking classifier outputs a classification result, thus enabling integration with existing semi-supervised classification methods. Moreover, we introduce regression distribution alignment (RDA), a complementary technique that further enhances RankUp's performance by refining pseudo-labels through distribution alignment. Despite its simplicity, RankUp, with or without RDA, achieves SOTA results in across a range of regression benchmarks, including computer vision, audio, and natural language processing tasks. Our code and log data are open-sourced at https://github.com/pm25/semi-supervised-regression.

Yi-Heng Lin, Wen-Hsuan Tseng, Li-Chin Chen et al.

The Consensus Auditory-Perceptual Evaluation of Voice is a widely employed tool in clinical voice quality assessment that is significant for streaming communication among clinical professionals and benchmarking for the determination of further treatment. Currently, because the assessment relies on experienced clinicians, it tends to be inconsistent, and thus, difficult to standardize. To address this problem, we propose to leverage lightly weighted automatic audio parameter extraction, to increase the clinical relevance, reduce the complexity, and enhance the interpretability of voice quality assessment. The proposed method utilizes age, sex, and five audio parameters: jitter, absolute jitter, shimmer, harmonic-to-noise ratio (HNR), and zero crossing. A classical machine learning approach is employed. The result reveals that our approach performs similar to state-of-the-art (SOTA) methods, and outperforms the latent representation obtained by using popular audio pre-trained models. This approach provide insights into the feasibility of different feature extraction approaches for voice evaluation. Audio parameters such as jitter and the HNR are proven to be suitable for characterizing voice quality attributes, such as roughness and strain. Conversely, pre-trained models exhibit limitations in effectively addressing noise-related scorings. This study contributes toward more comprehensive and precise voice quality evaluations, achieved by a comprehensively exploring diverse assessment methodologies.

Sahibzada Adil Shahzad, Ammarah Hashmi, Junichi Yamagishi et al.

Multimodal deepfakes can exhibit subtle visual artifacts and cross-modal inconsistencies, which remain challenging to detect, especially when detectors are trained primarily on curated synthetic forgeries. Such synthetic dependence can introduce dataset and generator bias, limiting scalability and robustness to unseen manipulations. We propose SAVe, a self-supervised audio-visual deepfake detection framework that learns entirely on authentic videos. SAVe generates on-the-fly, identity-preserving, region-aware self-blended pseudo-manipulations to emulate tampering artifacts, enabling the model to learn complementary visual cues across multiple facial granularities. To capture cross-modal evidence, SAVe also models lip-speech synchronization via an audio-visual alignment component that detects temporal misalignment patterns characteristic of audio-visual forgeries. Experiments on FakeAVCeleb and AV-LipSync-TIMIT demonstrate competitive in-domain performance and strong cross-dataset generalization, highlighting self-supervised learning as a scalable paradigm for multimodal deepfake detection.

Ammarah Hashmi, Sahibzada Adil Shahzad, Chia-Wen Lin et al.

Deep Learning has been successfully applied in diverse fields, and its impact on deepfake detection is no exception. Deepfakes are fake yet realistic synthetic content that can be used deceitfully for political impersonation, phishing, slandering, or spreading misinformation. Despite extensive research on unimodal deepfake detection, identifying complex deepfakes through joint analysis of audio and visual streams remains relatively unexplored. To fill this gap, this survey first provides an overview of audiovisual deepfake generation techniques, applications, and their consequences, and then provides a comprehensive review of state-of-the-art methods that combine audio and visual modalities to enhance detection accuracy, summarizing and critically analyzing their strengths and limitations. Furthermore, we discuss existing open source datasets for a deeper understanding, which can contribute to the research community and provide necessary information to beginners who want to analyze deep learning-based audiovisual methods for video forensics. By bridging the gap between unimodal and multimodal approaches, this paper aims to improve the effectiveness of deepfake detection strategies and guide future research in cybersecurity and media integrity.

Li-Chin Chen, Yi-Heng Lin, Li-Ning Peng et al.

Clinical guidelines underscore the importance of regularly monitoring and surveilling arteriovenous fistula (AVF) access in hemodialysis patients to promptly detect any dysfunction. Although phono-angiography/sound analysis overcomes the limitations of standardized AVF stenosis diagnosis tool, prior studies have depended on conventional feature extraction methods, restricting their applicability in diverse contexts. In contrast, representation learning captures fundamental underlying factors that can be readily transferred across different contexts. We propose an approach based on deep denoising autoencoders (DAEs) that perform dimensionality reduction and reconstruction tasks using the waveform obtained through one-level discrete wavelet transform, utilizing representation learning. Our results demonstrate that the latent representation generated by the DAE surpasses expectations with an accuracy of 0.93. The incorporation of noise-mixing and the utilization of a noise-to-clean scheme effectively enhance the discriminative capabilities of the latent representation. Moreover, when employed to identify patient-specific characteristics, the latent representation exhibited performance by surpassing an accuracy of 0.92. Appropriate light-weighted methods can restore the detection performance of the excessively reduced dimensionality version and enable operation on less computational devices. Our findings suggest that representation learning is a more feasible approach for extracting auscultation features in AVF, leading to improved generalization and applicability across multiple tasks. The manipulation of latent representations holds immense potential for future advancements. Further investigations in this area are promising and warrant continued exploration.

Xuankai Chang, Takashi Maekaku, Pengcheng Guo et al.

Self-supervised pretraining on speech data has achieved a lot of progress. High-fidelity representation of the speech signal is learned from a lot of untranscribed data and shows promising performance. Recently, there are several works focusing on evaluating the quality of self-supervised pretrained representations on various tasks without domain restriction, e.g. SUPERB. However, such evaluations do not provide a comprehensive comparison among many ASR benchmark corpora. In this paper, we focus on the general applications of pretrained speech representations, on advanced end-to-end automatic speech recognition (E2E-ASR) models. We select several pretrained speech representations and present the experimental results on various open-source and publicly available corpora for E2E-ASR. Without any modification of the back-end model architectures or training strategy, some of the experiments with pretrained representations, e.g., WSJ, WSJ0-2mix with HuBERT, reach or outperform current state-of-the-art (SOTA) recognition performance. Moreover, we further explore more scenarios for whether the pretraining representations are effective, such as the cross-language or overlapped speech. The scripts, configuratons and the trained models have been released in ESPnet to let the community reproduce our experiments and improve them.

Rong Chao, Wen-Huang Cheng, Moreno La Quatra et al. · gatech

This work aims to investigate the use of a recently proposed, attention-free, scalable state-space model (SSM), Mamba, for the speech enhancement (SE) task. In particular, we employ Mamba to deploy different regression-based SE models (SEMamba) with different configurations, namely basic, advanced, causal, and non-causal. Furthermore, loss functions either based on signal-level distances or metric-oriented are considered. Experimental evidence shows that SEMamba attains a competitive PESQ of 3.55 on the VoiceBank-DEMAND dataset with the advanced, non-causal configuration. A new state-of-the-art PESQ of 3.69 is also reported when SEMamba is combined with Perceptual Contrast Stretching (PCS). Compared against Transformed-based equivalent SE solutions, a noticeable FLOPs reduction up to ~12% is observed with the advanced non-causal configurations. Finally, SEMamba can be used as a pre-processing step before automatic speech recognition (ASR), showing competitive performance against recent SE solutions.

Po-Heng Chou, Da-Chih Lin, Hung-Yu Wei et al.

In this paper, a measurement-driven framework is proposed for early radio link failure (RLF) prediction in 5G non-standalone (NSA) railway environments. Using 10 Hz metro-train traces with serving and neighbor-cell indicators, we benchmark six models, namely CNN, LSTM, XGBoost, Anomaly Transformer, PatchTST, and TimesNet, under varied observation windows and prediction horizons. When the observation window is three seconds, TimesNet attains the highest F1 score with a three-second prediction horizon, while CNN provides a favorable accuracy-latency tradeoff with a two-second horizon, enabling proactive actions such as redundancy and adaptive handovers. The results indicate that deep temporal models can anticipate reliability degradations several seconds in advance using lightweight features available on commercial devices, offering a practical path to early-warning control in 5G-based railway systems.

Chih-Ning Chen, Jen-Cheng Hou, Hsin-Min Wang et al.

In existing Audio-Visual Speech Enhancement (AVSE) methods, objectives such as Scale-Invariant Signal-to-Noise Ratio (SI-SNR) and Mean Squared Error (MSE) are widely used; however, they often correlate poorly with perceptual quality and provide limited interpretability for optimization. This work proposes a reinforcement learning-based AVSE framework with a Large Language Model (LLM)-based interpretable reward model. An audio LLM generates natural language descriptions of enhanced speech, which are converted by a sentiment analysis model into a 1-5 rating score serving as the PPO reward for fine-tuning a pretrained AVSE model. Compared with scalar metrics, LLM-generated feedback is semantically rich and explicitly describes improvements in speech quality. Experiments on the 4th COG-MHEAR AVSE Challenge (AVSEC-4) dataset show that the proposed method outperforms a supervised baseline and a DNSMOS-based RL baseline in PESQ, STOI, neural quality metrics, and subjective listening tests.

Szu-Wei Fu, Kuo-Hsuan Hung, Yu Tsao et al.

Speech quality estimation has recently undergone a paradigm shift from human-hearing expert designs to machine-learning models. However, current models rely mainly on supervised learning, which is time-consuming and expensive for label collection. To solve this problem, we propose VQScore, a self-supervised metric for evaluating speech based on the quantization error of a vector-quantized-variational autoencoder (VQ-VAE). The training of VQ-VAE relies on clean speech; hence, large quantization errors can be expected when the speech is distorted. To further improve correlation with real quality scores, domain knowledge of speech processing is incorporated into the model design. We found that the vector quantization mechanism could also be used for self-supervised speech enhancement (SE) model training. To improve the robustness of the encoder for SE, a novel self-distillation mechanism combined with adversarial training is introduced. In summary, the proposed speech quality estimation method and enhancement models require only clean speech for training without any label requirements. Experimental results show that the proposed VQScore and enhancement model are competitive with supervised baselines. The code will be released after publication.

Shuntaro Suzuki, Chia-Chun Dan Hsu, Yu Tsao et al.

Decoding linguistically meaningful representations from non-invasive neural recordings remains a central challenge in neural speech decoding. Among available neuroimaging modalities, magnetoencephalography (MEG) provides a safe and repeatable means of mapping speech-related cortical dynamics, yet its low signal-to-noise ratio and high temporal dimensionality continue to hinder robust decoding. In this work, we introduce MEGState, a novel architecture for phoneme decoding from MEG signals that captures fine-grained cortical responses evoked by auditory stimuli. Extensive experiments on the LibriBrain dataset demonstrate that MEGState consistently surpasses baseline model across multiple evaluation metrics. These findings highlight the potential of MEG-based phoneme decoding as a scalable pathway toward non-invasive brain-computer interfaces for speech.

Ying-Ren Chien, Po-Heng Chou, You-Jie Peng et al.

To effectively process impulse noise for narrowband powerline communications (NB-PLCs) transceivers, capturing comprehensive statistics of nonperiodic asynchronous impulsive noise (APIN) is a critical task. However, existing mathematical noise generative models only capture part of the characteristics of noise. In this study, we propose a novel generative adversarial network (GAN) called noise generation GAN (NGGAN) that learns the complicated characteristics of practically measured noise samples for data synthesis. To closely match the statistics of complicated noise over the NB-PLC systems, we measured the NB-PLC noise via the analog coupling and bandpass filtering circuits of a commercial NB-PLC modem to build a realistic dataset. To train NGGAN, we adhere to the following principles: 1) we design the length of input signals that the NGGAN model can fit to facilitate cyclostationary noise generation; 2) the Wasserstein distance is used as a loss function to enhance the similarity between the generated noise and training data; and 3) to measure the similarity performances of GAN-based models based on the mathematical and practically measured datasets, we conduct both quantitative and qualitative analyses. The training datasets include: 1) a piecewise spectral cyclostationary Gaussian model (PSCGM); 2) a frequency-shift (FRESH) filter; and 3) practical measurements from NB-PLC systems. Simulation results demonstrate that the generated noise samples from the proposed NGGAN are highly close to the real noise samples. The principal component analysis (PCA) scatter plots and Fréchet inception distance (FID) analysis have shown that NGGAN outperforms other GAN-based models by generating noise samples with superior fidelity and higher diversity.