Ming Li

Huali Zhou, Yueqian Lin, Yao Shi et al.

Although Singing Voice Synthesis (SVS) has made great strides with Text-to-Speech (TTS) techniques, multilingual singing voice modeling remains relatively unexplored. This paper presents BiSinger, a bilingual pop SVS system for English and Chinese Mandarin. Current systems require separate models per language and cannot accurately represent both Chinese and English, hindering code-switch SVS. To address this gap, we design a shared representation between Chinese and English singing voices, achieved by using the CMU dictionary with mapping rules. We fuse monolingual singing datasets with open-source singing voice conversion techniques to generate bilingual singing voices while also exploring the potential use of bilingual speech data. Experiments affirm that our language-independent representation and incorporation of related datasets enable a single model with enhanced performance in English and code-switch SVS while maintaining Chinese song performance. Audio samples are available at https://bisinger-svs.github.io.

Qian Niu, Junyu Liu, Ziqian Bi et al.

This comprehensive review explores the intersection of Large Language Models (LLMs) and cognitive science, examining similarities and differences between LLMs and human cognitive processes. We analyze methods for evaluating LLMs cognitive abilities and discuss their potential as cognitive models. The review covers applications of LLMs in various cognitive fields, highlighting insights gained for cognitive science research. We assess cognitive biases and limitations of LLMs, along with proposed methods for improving their performance. The integration of LLMs with cognitive architectures is examined, revealing promising avenues for enhancing artificial intelligence (AI) capabilities. Key challenges and future research directions are identified, emphasizing the need for continued refinement of LLMs to better align with human cognition. This review provides a balanced perspective on the current state and future potential of LLMs in advancing our understanding of both artificial and human intelligence.

Ming Li, Ruihong Huang

News Discourse Profiling seeks to scrutinize the event-related role of each sentence in a news article and has been proven useful across various downstream applications. Specifically, within the context of a given news discourse, each sentence is assigned to a pre-defined category contingent upon its depiction of the news event structure. However, existing approaches suffer from an inadequacy of available human-annotated data, due to the laborious and time-intensive nature of generating discourse-level annotations. In this paper, we present a novel approach, denoted as Intra-document Contrastive Learning with Distillation (ICLD), for addressing the news discourse profiling task, capitalizing on its unique structural characteristics. Notably, we are the first to apply a semi-supervised methodology within this task paradigm, and evaluation demonstrates the effectiveness of the presented approach.

Ming Li, Ruihong Huang

Rhetorical Structure Theory based Discourse Parsing (RST-DP) explores how clauses, sentences, and large text spans compose a whole discourse and presents the rhetorical structure as a hierarchical tree. Existing RST parsing pipelines construct rhetorical structures without the knowledge of document-level content structures, which causes relatively low performance when predicting the discourse relations for large text spans. Recognizing the value of high-level content-related information in facilitating discourse relation recognition, we propose a novel pipeline for RST-DP that incorporates structure-aware news content sentence representations derived from the task of News Discourse Profiling. By incorporating only a few additional layers, this enhanced pipeline exhibits promising performance across various RST parsing metrics.

Ming Li, Ruihong Huang

Complex feature extractors are widely employed for text representation building. However, these complex feature extractors make the NLP systems prone to overfitting especially when the downstream training datasets are relatively small, which is the case for several discourse parsing tasks. Thus, we propose an alternative lightweight neural architecture that removes multiple complex feature extractors and only utilizes learnable self-attention modules to indirectly exploit pretrained neural language models, in order to maximally preserve the generalizability of pre-trained language models. Experiments on three common discourse parsing tasks show that powered by recent pretrained language models, the lightweight architecture consisting of only two self-attention layers obtains much better generalizability and robustness. Meanwhile, it achieves comparable or even better system performance with fewer learnable parameters and less processing time.

Zhiying Jiang, Rui Wang, Dongbo Bu et al.

We aim to bridge the gap between our common-sense few-sample human learning and large-data machine learning. We derive a theory of human-like few-shot learning from von-Neuman-Landauer's principle. modelling human learning is difficult as how people learn varies from one to another. Under commonly accepted definitions, we prove that all human or animal few-shot learning, and major models including Free Energy Principle and Bayesian Program Learning that model such learning, approximate our theory, under Church-Turing thesis. We find that deep generative model like variational autoencoder (VAE) can be used to approximate our theory and perform significantly better than baseline models including deep neural networks, for image recognition, low resource language processing, and character recognition.

Beilong Tang, Bang Zeng, Ming Li

We propose TSELM, a novel target speaker extraction network that leverages discrete tokens and language models. TSELM utilizes multiple discretized layers from WavLM as input tokens and incorporates cross-attention mechanisms to integrate target speaker information. Language models are employed to capture the sequence dependencies, while a scalable HiFi-GAN is used to reconstruct the audio from the tokens. By applying a cross-entropy loss, TSELM models the probability distribution of output tokens, thus converting the complex regression problem of audio generation into a classification task. Experimental results show that TSELM achieves excellent results in speech quality and comparable results in speech intelligibility.

Zhixun Chen, Ming Li, Yuxuan Huang et al.

Large Language Model (LLM) agents have demonstrated remarkable generalization capabilities across multi-domain tasks. Existing agent tuning approaches typically employ supervised finetuning on entire expert trajectories. However, behavior-cloning of full trajectories can introduce expert bias and weaken generalization to states not covered by the expert data. Additionally, critical steps, such as planning, complex reasoning for intermediate subtasks, and strategic decision-making, are essential to success in agent tasks, so learning these steps is the key to improving LLM agents. For more effective and efficient agent tuning, we propose ATLaS that identifies the critical steps in expert trajectories and finetunes LLMs solely on these steps with reduced costs. By steering the training's focus to a few critical steps, our method mitigates the risk of overfitting entire trajectories and promotes generalization across different environments and tasks. In extensive experiments, an LLM finetuned on only 30% critical steps selected by ATLaS outperforms the LLM finetuned on all steps and recent open-source LLM agents. ATLaS maintains and improves base LLM skills as generalist agents interacting with diverse environments.

Yifang Xu, Benxiang Zhai, Yunzhuo Sun et al.

Recent advancements in diffusion-based technologies have made significant strides, particularly in identity-preserved portrait generation (IPG). However, when using multiple reference images from the same ID, existing methods typically produce lower-fidelity portraits and struggle to customize face attributes precisely. To address these issues, this paper presents HiFi-Portrait, a high-fidelity method for zero-shot portrait generation. Specifically, we first introduce the face refiner and landmark generator to obtain fine-grained multi-face features and 3D-aware face landmarks. The landmarks include the reference ID and the target attributes. Then, we design HiFi-Net to fuse multi-face features and align them with landmarks, which improves ID fidelity and face control. In addition, we devise an automated pipeline to construct an ID-based dataset for training HiFi-Portrait. Extensive experimental results demonstrate that our method surpasses the SOTA approaches in face similarity and controllability. Furthermore, our method is also compatible with previous SDXL-based works.

Ming Li, Naiyin Liu, Xiaofeng Pan et al.

Since clicks usually contain heavy noise, increasing research efforts have been devoted to modeling implicit negative user behaviors (i.e., non-clicks). However, they either rely on explicit negative user behaviors (e.g., dislikes) or simply treat non-clicks as negative feedback, failing to learn negative user interests comprehensively. In such situations, users may experience fatigue because of seeing too many similar recommendations. In this paper, we propose Fatigue-Aware Network (FAN), a novel CTR model that directly perceives user fatigue from non-clicks. Specifically, we first apply Fourier Transformation to the time series generated from non-clicks, obtaining its frequency spectrum which contains comprehensive information about user fatigue. Then the frequency spectrum is modulated by category information of the target item to model the bias that both the upper bound of fatigue and users' patience is different for different categories. Moreover, a gating network is adopted to model the confidence of user fatigue and an auxiliary task is designed to guide the learning of user fatigue, so we can obtain a well-learned fatigue representation and combine it with user interests for the final CTR prediction. Experimental results on real-world datasets validate the superiority of FAN and online A/B tests also show FAN outperforms representative CTR models significantly.

Yucong Zhang, Xin Zou, Jinshan Yang et al.

This paper presents the Multimodal Laryngoscopic Video Analyzing System (MLVAS), a novel system that leverages both audio and video data to automatically extract key video segments and metrics from raw laryngeal videostroboscopic videos for assisted clinical assessment. The system integrates video-based glottis detection with an audio keyword spotting method to analyze both video and audio data, identifying patient vocalizations and refining video highlights to ensure optimal inspection of vocal fold movements. Beyond key video segment extraction from the raw laryngeal videos, MLVAS is able to generate effective audio and visual features for Vocal Fold Paralysis (VFP) detection. Pre-trained audio encoders are utilized to encode the patient voice to get the audio features. Visual features are generated by measuring the angle deviation of both the left and right vocal folds to the estimated glottal midline on the segmented glottis masks. To get better masks, we introduce a diffusion-based refinement that follows traditional U-Net segmentation to reduce false positives. We conducted several ablation studies to demonstrate the effectiveness of each module and modalities in the proposed MLVAS. The experimental results on a public segmentation dataset show the effectiveness of our proposed segmentation module. In addition, unilateral VFP classification results on a real-world clinic dataset demonstrate MLVAS's ability of providing reliable and objective metrics as well as visualization for assisted clinical diagnosis.

Lifan Jiang, Zhihui Wang, Changmiao Wang et al.

Object detection, a quintessential task in the realm of perceptual computing, can be tackled using a generative methodology. In the present study, we introduce a novel framework designed to articulate object detection as a denoising diffusion process, which operates on the perturbed bounding boxes of annotated entities. This framework, termed \textbf{ConsistencyDet}, leverages an innovative denoising concept known as the Consistency Model. The hallmark of this model is its self-consistency feature, which empowers the model to map distorted information from any time step back to its pristine state, thereby realizing a \textbf{``few-step denoising''} mechanism. Such an attribute markedly elevates the operational efficiency of the model, setting it apart from the conventional Diffusion Model. Throughout the training phase, ConsistencyDet initiates the diffusion sequence with noise-infused boxes derived from the ground-truth annotations and conditions the model to perform the denoising task. Subsequently, in the inference stage, the model employs a denoising sampling strategy that commences with bounding boxes randomly sampled from a normal distribution. Through iterative refinement, the model transforms an assortment of arbitrarily generated boxes into definitive detections. Comprehensive evaluations employing standard benchmarks, such as MS-COCO and LVIS, corroborate that ConsistencyDet surpasses other leading-edge detectors in performance metrics. Our code is available at https://anonymous.4open.science/r/ConsistencyDet-37D5.

Ming Gao, Hang Chen, Jun Du et al.

Smart home technology has gained widespread adoption, facilitating effortless control of devices through voice commands. However, individuals with dysarthria, a motor speech disorder, face challenges due to the variability of their speech. This paper addresses the wake-up word spotting (WWS) task for dysarthric individuals, aiming to integrate them into real-world applications. To support this, we release the open-source Mandarin Dysarthria Speech Corpus (MDSC), a dataset designed for dysarthric individuals in home environments. MDSC encompasses information on age, gender, disease types, and intelligibility evaluations. Furthermore, we perform comprehensive experimental analysis on MDSC, highlighting the challenges encountered. We also develop a customized dysarthria WWS system that showcases robustness in handling intelligibility and achieving exceptional performance. MDSC will be released on https://www.aishelltech.com/AISHELL_6B.

Jiyang Tang, Ming Li

In this paper, we propose an end-to-end Mandarin tone classification method from continuous speech utterances utilizing both the spectrogram and the short-term context information as the input. Both spectrograms and context segment features are used to train the tone classifier. We first divide the spectrogram frames into syllable segments using force alignment results produced by an ASR model. Then we extract the short-term segment features to capture the context information across multiple syllables. Feeding both the spectrogram and the short-term context segment features into an end-to-end model could significantly improve the performance. Experiments are performed on a large-scale open-source Mandarin speech dataset to evaluate the proposed method. Results show that this method improves the classification accuracy from 79.5% to 92.6% on the AISHELL3 database.

Hamidreza Shahidi, Ming Li, Jimmy Lin

A number of researchers have recently questioned the necessity of increasingly complex neural network (NN) architectures. In particular, several recent papers have shown that simpler, properly tuned models are at least competitive across several NLP tasks. In this work, we show that this is also the case for text generation from structured and unstructured data. We consider neural table-to-text generation and neural question generation (NQG) tasks for text generation from structured and unstructured data, respectively. Table-to-text generation aims to generate a description based on a given table, and NQG is the task of generating a question from a given passage where the generated question can be answered by a certain sub-span of the passage using NN models. Experimental results demonstrate that a basic attention-based seq2seq model trained with the exponential moving average technique achieves the state of the art in both tasks. Code is available at https://github.com/h-shahidi/2birds-gen.

Wei Yang, Yuqing Xie, Aileen Lin et al.

We demonstrate an end-to-end question answering system that integrates BERT with the open-source Anserini information retrieval toolkit. In contrast to most question answering and reading comprehension models today, which operate over small amounts of input text, our system integrates best practices from IR with a BERT-based reader to identify answers from a large corpus of Wikipedia articles in an end-to-end fashion. We report large improvements over previous results on a standard benchmark test collection, showing that fine-tuning pretrained BERT with SQuAD is sufficient to achieve high accuracy in identifying answer spans.

Kerui Chen, Jianrong Zhang, Ming Li et al.

Existing stylized motion generation models have shown their remarkable ability to understand specific style information from the style motion, and insert it into the content motion. However, capturing intra-style diversity, where a single style should correspond to diverse motion variations, remains a significant challenge. In this paper, we propose a clustering-based framework, ClusterStyle, to address this limitation. Instead of learning an unstructured embedding from each style motion, we leverage a set of prototypes to effectively model diverse style patterns across motions belonging to the same style category. We consider two types of style diversity: global-level diversity among style motions of the same category, and local-level diversity within the temporal dynamics of motion sequences. These components jointly shape two structured style embedding spaces, i.e., global and local, optimized via alignment with non-learnable prototype anchors. Furthermore, we augment the pretrained text-to-motion generation model with the Stylistic Modulation Adapter (SMA) to integrate the style features. Extensive experiments demonstrate that our approach outperforms existing state-of-the-art models in stylized motion generation and motion style transfer.

Zhangyu Lai, Yilin Lu, Xinyang Li et al.

While existing anomaly synthesis methods have made remarkable progress, achieving both realism and diversity in synthesis remains a major obstacle. To address this, we propose AnomalyPainter, a zero-shot framework that breaks the diversity-realism trade-off dilemma through synergizing Vision Language Large Model (VLLM), Latent Diffusion Model (LDM), and our newly introduced texture library Tex-9K. Tex-9K is a professional texture library containing 75 categories and 8,792 texture assets crafted for diverse anomaly synthesis. Leveraging VLLM's general knowledge, reasonable anomaly text descriptions are generated for each industrial object and matched with relevant diverse textures from Tex-9K. These textures then guide the LDM via ControlNet to paint on normal images. Furthermore, we introduce Texture-Aware Latent Init to stabilize the natural-image-trained ControlNet for industrial images. Extensive experiments show that AnomalyPainter outperforms existing methods in realism, diversity, and generalization, achieving superior downstream performance.

Junzhe Li, Sifan Zhou, Liya Guo et al.

Unified multimodal models (UMMs) have emerged as a powerful paradigm in fundamental cross-modality research, demonstrating significant potential in both image understanding and generation. However, existing research in the face domain primarily faces two challenges: $\textbf{(1)}$ $\textbf{fragmentation development}$, with existing methods failing to unify understanding and generation into a single one, hindering the way to artificial general intelligence. $\textbf{(2) lack of fine-grained facial attributes}$, which are crucial for high-fidelity applications. To handle those issues, we propose $\textbf{UniF$^2$ace}$, $\textit{the first UMM specifically tailored for fine-grained face understanding and generation}$. $\textbf{First}$, we introduce a novel theoretical framework with a Dual Discrete Diffusion (D3Diff) loss, unifying masked generative models with discrete score matching diffusion and leading to a more precise approximation of the negative log-likelihood. Moreover, this D3Diff significantly enhances the model's ability to synthesize high-fidelity facial details aligned with text input. $\textbf{Second}$, we propose a multi-level grouped Mixture-of-Experts architecture, adaptively incorporating the semantic and identity facial embeddings to complement the attribute forgotten phenomenon in representation evolvement. $\textbf{Finally}$, to this end, we construct UniF$^2$aceD-1M, a large-scale dataset comprising 130K fine-grained image-caption pairs and 1M visual question-answering pairs, spanning a much wider range of facial attributes than existing datasets. Extensive experiments demonstrate that UniF$^2$ace outperforms existing models with a similar scale in both understanding and generation tasks, with 7.1\% higher Desc-GPT and 6.6\% higher VQA-score, respectively.

Qingshu Xu, Hong Jiao, Tianyi Zhou et al.

Accurate alignment of items to content standards is critical for valid score interpretation in large-scale assessments. This study evaluates three automated paradigms for aligning items with four domain and nineteen skill labels. First, we extracted embeddings and trained multiple classical supervised machine learning models, and further investigated the impact of dimensionality reduction on model performance. Second, we fine-tuned eight BERT model and its variants for both domain and skill alignment. Third, we explored ensemble learning with majority voting and stacking with multiple meta-models. The DeBERTa-v3-base achieved the highest weighted-average F1 score of 0.950 for domain alignment while the RoBERTa-large yielded the highest F1 score of 0.869 for skill alignment. Ensemble models did not surpass the best-performing language models. Dimension reduction enhanced linear classifiers based on embeddings but did not perform better than language models. This study demonstrated different methods in automated item alignment to content standards.}

Sydney Peters, Nan Zhang, Hong Jiao et al.

Item difficulty plays a crucial role in test performance, interpretability of scores, and equity for all test-takers, especially in large-scale assessments. Traditional approaches to item difficulty modeling rely on field testing and classical test theory (CTT)-based item analysis or item response theory (IRT) calibration, which can be time-consuming and costly. To overcome these challenges, text-based approaches leveraging machine learning and language models, have emerged as promising alternatives. This paper reviews and synthesizes 37 articles on automated item difficulty prediction in large-scale assessment settings published through May 2025. For each study, we delineate the dataset, difficulty parameter, subject domain, item type, number of items, training and test data split, input, features, model, evaluation criteria, and model performance outcomes. Results showed that although classic machine learning models remain relevant due to their interpretability, state-of-the-art language models, using both small and large transformer-based architectures, can capture syntactic and semantic patterns without the need for manual feature engineering. Uniquely, model performance outcomes were summarized to serve as a benchmark for future research and overall, text-based methods have the potential to predict item difficulty with root mean square error (RMSE) as low as 0.165, Pearson correlation as high as 0.87, and accuracy as high as 0.806. The review concludes by discussing implications for practice and outlining future research directions for automated item difficulty modeling.

Silin Chen, Ziqian Bi, Junyu Liu et al.

This book provides a comprehensive introduction to the foundational concepts of machine learning (ML) and deep learning (DL). It bridges the gap between theoretical mathematics and practical application, focusing on Python as the primary programming language for implementing key algorithms and data structures. The book covers a wide range of topics, including basic and advanced Python programming, fundamental mathematical operations, matrix operations, linear algebra, and optimization techniques crucial for training ML and DL models. Advanced subjects like neural networks, optimization algorithms, and frequency domain methods are also explored, along with real-world applications of large language models (LLMs) and artificial intelligence (AI) in big data management. Designed for both beginners and advanced learners, the book emphasizes the critical role of mathematical principles in developing scalable AI solutions. Practical examples and Python code are provided throughout, ensuring readers gain hands-on experience in applying theoretical knowledge to solve complex problems in ML, DL, and big data analytics.

Ming Li, Han Chen, Chenguang Wang et al.

Large language models (LLMs) still lack delicate controllability over their responses, which is critical to enhancing their performance and the user experience. However, curating supervised fine-tuning (SFT) datasets to improve LLM controllability usually relies on human experts or proprietary LLMs, which requires additional costs. To bridge this gap, we propose Rule-based Data Recycling (RuleR), a data augmentation method incorporating multiple constraints into the original data samples according to predefined rules, which creates new training tasks to consolidate the controllability of LLMs. Instead of creating new data from scratch, RuleR "recycles" existing data by simply applying rule-based edits to their responses and appending the rule-instructions in their original instructions. Experimental results demonstrate RuleR's effectiveness in improving LLM controllability while maintaining general instruction-following capabilities.

Weiqing Wang, Xiaoyi Qin, Ming Li

In this paper, we present the speaker diarization system for the Multi-channel Multi-party Meeting Transcription Challenge (M2MeT) from team DKU_DukeECE. As the highly overlapped speech exists in the dataset, we employ an x-vector-based target-speaker voice activity detection (TS-VAD) to find the overlap between speakers. For the single-channel scenario, we separately train a model for each of the 8 channels and fuse the results. We also employ the cross-channel self-attention to further improve the performance, where the non-linear spatial correlations between different channels are learned and fused. Experimental results on the evaluation set show that the single-channel TS-VAD reduces the DER by over 75% from 12.68\% to 3.14%. The multi-channel TS-VAD further reduces the DER by 28% and achieves a DER of 2.26%. Our final submitted system achieves a DER of 2.98% on the AliMeeting test set, which ranks 1st in the M2MET challenge.

Ziyi Chen, Hua Hua, Yuxiang Zhang et al.

The voice conversion task is to modify the speaker identity of continuous speech while preserving the linguistic content. Generally, the naturalness and similarity are two main metrics for evaluating the conversion quality, which has been improved significantly in recent years. This paper presents the HCCL-DKU entry for the fake audio generation task of the 2022 ICASSP ADD challenge. We propose a novel ppg-based voice conversion model that adopts a fully end-to-end structure. Experimental results show that the proposed method outperforms other conversion models, including Tacotron-based and Fastspeech-based models, on conversion quality and spoofing performance against anti-spoofing systems. In addition, we investigate several post-processing methods for better spoofing power. Finally, we achieve second place with a deception success rate of 0.916 in the ADD challenge.

Zexin Cai, Ming Li

In this paper, we propose an invertible deep learning framework called INVVC for voice conversion. It is designed against the possible threats that inherently come along with voice conversion systems. Specifically, we develop an invertible framework that makes the source identity traceable. The framework is built on a series of invertible $1\times1$ convolutions and flows consisting of affine coupling layers. We apply the proposed framework to one-to-one voice conversion and many-to-one conversion using parallel training data. Experimental results show that this approach yields impressive performance on voice conversion and, moreover, the converted results can be reversed back to the source inputs utilizing the same parameters as in forwarding.

Haoxu Wang, Yan Jia, Zeqing Zhao et al.

Wake-up word detection models are widely used in real life, but suffer from severe performance degradation when encountering adversarial samples. In this paper we discuss the concept of confusing words in adversarial samples. Confusing words are commonly encountered, which are various kinds of words that sound similar to the predefined keywords. To enhance the wake word detection system's robustness against confusing words, we propose several methods to generate the adversarial confusing samples for simulating real confusing words scenarios in which we usually do not have any real confusing samples in the training set. The generated samples include concatenated audio, synthesized data, and partially masked keywords. Moreover, we use a domain embedding concatenated system to improve the performance. Experimental results show that the adversarial samples generated in our approach help improve the system's robustness in both the common scenario and the confusing words scenario. In addition, we release the confusing words testing database called HI-MIA-CW for future research.

Haozhe Zhang, Zexin Cai, Xiaoyi Qin et al.

Nowadays, as more and more systems achieve good performance in traditional voice conversion (VC) tasks, people's attention gradually turns to VC tasks under extreme conditions. In this paper, we propose a novel method for zero-shot voice conversion. We aim to obtain intermediate representations for speaker-content disentanglement of speech to better remove speaker information and get pure content information. Accordingly, our proposed framework contains a module that removes the speaker information from the acoustic feature of the source speaker. Moreover, speaker information control is added to our system to maintain the voice cloning performance. The proposed system is evaluated by subjective and objective metrics. Results show that our proposed system significantly reduces the trade-off problem in zero-shot voice conversion, while it also manages to have high spoofing power to the speaker verification system.

Xiaoyi Qin, Na Li, Chao Weng et al.

Recently, the attention mechanism such as squeeze-and-excitation module (SE) and convolutional block attention module (CBAM) has achieved great success in deep learning-based speaker verification system. This paper introduces an alternative effective yet simple one, i.e., simple attention module (SimAM), for speaker verification. The SimAM module is a plug-and-play module without extra modal parameters. In addition, we propose a noisy label detection method to iteratively filter out the data samples with a noisy label from the training data, considering that a large-scale dataset labeled with human annotation or other automated processes may contain noisy labels. Data with the noisy label may over parameterize a deep neural network (DNN) and result in a performance drop due to the memorization effect of the DNN. Experiments are conducted on VoxCeleb dataset. The speaker verification model with SimAM achieves the 0.675% equal error rate (EER) on VoxCeleb1 original test trials. Our proposed iterative noisy label detection method further reduces the EER to 0.643%.

Qingjian Lin, Lin Yang, Xuyang Wang et al.

With the development of deep learning, automatic speaker verification has made considerable progress over the past few years. However, to design a lightweight and robust system with limited computational resources is still a challenging problem. Traditionally, a speaker verification system is symmetrical, indicating that the same embedding extraction model is applied for both enrollment and verification in inference. In this paper, we come up with an innovative asymmetric structure, which takes the large-scale ECAPA-TDNN model for enrollment and the small-scale ECAPA-TDNNLite model for verification. As a symmetrical system, our proposed ECAPA-TDNNLite model achieves an EER of 3.07% on the Voxceleb1 original test set with only 11.6M FLOPS. Moreover, the asymmetric structure further reduces the EER to 2.31%, without increasing any computational costs during verification.

Danwei Cai, Ming Li

This report describes the submission of the DKU-DukeECE team to the self-supervision speaker verification task of the 2021 VoxCeleb Speaker Recognition Challenge (VoxSRC). Our method employs an iterative labeling framework to learn self-supervised speaker representation based on a deep neural network (DNN). The framework starts with training a self-supervision speaker embedding network by maximizing agreement between different segments within an utterance via a contrastive loss. Taking advantage of DNN's ability to learn from data with label noise, we propose to cluster the speaker embedding obtained from the previous speaker network and use the subsequent class assignments as pseudo labels to train a new DNN. Moreover, we iteratively train the speaker network with pseudo labels generated from the previous step to bootstrap the discriminative power of a DNN. Also, visual modal data is incorporated in this self-labeling framework. The visual pseudo label and the audio pseudo label are fused with a cluster ensemble algorithm to generate a robust supervisory signal for representation learning. Our submission achieves an equal error rate (EER) of 5.58% and 5.59% on the challenge development and test set, respectively.

Weiqing Wang, Danwei Cai, Qingjian Lin et al.

This report describes the submission of the DKU-DukeECE-Lenovo team to the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2021 track 4. Our system including a voice activity detection (VAD) model, a speaker embedding model, two clustering-based speaker diarization systems with different similarity measurements, two different overlapped speech detection (OSD) models, and a target-speaker voice activity detection (TS-VAD) model. Our final submission, consisting of 5 independent systems, achieves a DER of 5.07% on the challenge test set.

Ziqi Xu, Jingcheng Li, Yanjun Pan et al.

Cooperative vehicle platooning significantly improves highway safety, fuel efficiency, and traffic flow. In this model, a set of vehicles move in line formation and coordinate acceleration, braking, and steering using a combination of physical sensing and vehicle-to-vehicle (V2V) messaging. The authenticity and integrity of the V2V messages are paramount to safety. For this reason, recent V2V and V2X standards support the integration of a PKI. However, a PKI cannot bind a vehicle's digital identity to the vehicle's physical state (location, velocity, etc.). As a result, a vehicle with valid cryptographic credentials can impact platoons from a remote location. In this paper, we seek to provide the missing link between the physical and the digital world in the context of vehicle platooning. We propose a new access control protocol we call Proof-of-Following (PoF) that verifies the following distance between a candidate and a verifier. The main idea is to draw security from the common, but constantly changing environment experienced by the closely traveling vehicles. We use the large-scale fading effect of ambient RF signals as a common source of randomness to construct a {\em PoF} primitive. The correlation of large-scale fading is an ideal candidate for the mobile outdoor environment because it exponentially decays with distance and time. We evaluate our PoF protocol on an experimental platoon of two vehicles in freeway, highway, and urban driving conditions. We demonstrate that the PoF withstands both the pre-recording and following attacks with overwhelming probability.

Yuanyuan Bao, Yanze Xu, Na Xu et al.

Nowadays, there is a strong need to deploy the target speaker separation (TSS) model on mobile devices with a limitation of the model size and computational complexity. To better perform TSS for mobile voice communication, we first make a dual-channel dataset based on a specific scenario, LibriPhone. Specifically, to better mimic the real-case scenario, instead of simulating from the single-channel dataset, LibriPhone is made by simultaneously replaying pairs of utterances from LibriSpeech by two professional artificial heads and recording by two built-in microphones of the mobile. Then, we propose a lightweight time-frequency domain separation model, LSTM-Former, which is based on the LSTM framework with source-to-noise ratio (SI-SNR) loss. For the experiments on Libri-Phone, we explore the dual-channel LSTMFormer model and a single-channel version by a random single channel of Libri-Phone. Experimental result shows that the dual-channel LSTM-Former outperforms the single-channel LSTMFormer with relative 25% improvement. This work provides a feasible solution for the TSS task on mobile devices, playing back and recording multiple data sources in real application scenarios for getting dual-channel real data can assist the lightweight model to achieve higher performance.

Yaogen Yang, Haozhe Zhang, Xiaoyi Qin et al.

Building cross-lingual voice conversion (VC) systems for multiple speakers and multiple languages has been a challenging task for a long time. This paper describes a parallel non-autoregressive network to achieve bilingual and code-switched voice conversion for multiple speakers when there are only mono-lingual corpora for each language. We achieve cross-lingual VC between Mandarin speech with multiple speakers and English speech with multiple speakers by applying bilingual bottleneck features. To boost voice cloning performance, we use an adversarial speaker classifier with a gradient reversal layer to reduce the source speaker's information from the output of encoder. Furthermore, in order to improve speaker similarity between reference speech and converted speech, we adopt an embedding consistency loss between the synthesized speech and its natural reference speech in our network. Experimental results show that our proposed method can achieve high quality converted speech with mean opinion score (MOS) around 4. The conversion system performs well in terms of speaker similarity for both in-set speaker conversion and out-set-of one-shot conversion.

Ziang Zhou, Yanze Xu, Ming Li

Textual escalation detection has been widely applied to e-commerce companies' customer service systems to pre-alert and prevent potential conflicts. Similarly, in public areas such as airports and train stations, where many impersonal conversations frequently take place, acoustic-based escalation detection systems are also useful to enhance passengers' safety and maintain public order. To this end, we introduce a system based on acoustic-lexical features to detect escalation from speech, Voice Activity Detection (VAD) and label smoothing are adopted to further enhance the performance in our experiments. Considering a small set of training and development data, we also employ transfer learning on several wellknown emotional detection datasets, i.e. RAVDESS, CREMA-D, to learn advanced emotional representations that is then applied to the conversational escalation detection task. On the development set, our proposed system achieves 81.5% unweighted average recall (UAR) which significantly outperforms the baseline with 72.2% UAR.

Tinglong Zhu, Xiaoyi Qin, Ming Li

Although deep neural networks are successful for many tasks in the speech domain, the high computational and memory costs of deep neural networks make it difficult to directly deploy highperformance Neural Network systems on low-resource embedded devices. There are several mechanisms to reduce the size of the neural networks i.e. parameter pruning, parameter quantization, etc. This paper focuses on how to apply binary neural networks to the task of speaker verification. The proposed binarization of training parameters can largely maintain the performance while significantly reducing storage space requirements and computational costs. Experiment results show that, after binarizing the Convolutional Neural Network, the ResNet34-based network achieves an EER of around 5% on the Voxceleb1 testing dataset and even outperforms the traditional real number network on the text-dependent dataset: Xiaole while having a 32x memory saving.

Weiqing Wang, Qingjian Lin, Danwei Cai et al.

In this paper, we present the submitted system for the third DIHARD Speech Diarization Challenge from the DKU-Duke-Lenovo team. Our system consists of several modules: voice activity detection (VAD), segmentation, speaker embedding extraction, attentive similarity scoring, agglomerative hierarchical clustering. In addition, the target speaker VAD (TSVAD) is used for the phone call data to further improve the performance. Our final submitted system achieves a DER of 15.43% for the core evaluation set and 13.39% for the full evaluation set on task 1, and we also get a DER of 21.63% for core evaluation set and 18.90% for full evaluation set on task 2.

Weicheng Cai, Ming Li

This paper proposes a unified deep speaker embedding framework for modeling speech data with different sampling rates. Considering the narrowband spectrogram as a sub-image of the wideband spectrogram, we tackle the joint modeling problem of the mixed-bandwidth data in an image classification manner. From this perspective, we elaborate several mixed-bandwidth joint training strategies under different training and test data scenarios. The proposed systems are able to flexibly handle the mixed-bandwidth speech data in a single speaker embedding model without any additional downsampling, upsampling, bandwidth extension, or padding operations. We conduct extensive experimental studies on the VoxCeleb1 dataset. Furthermore, the effectiveness of the proposed approach is validated by the SITW and NIST SRE 2016 datasets.

Xiaoyi Qin, Yaogen Yang, Lin Yang et al.

In this paper, we focus on improving the performance of the text-dependent speaker verification system in the scenario of limited training data. The speaker verification system deep learning based text-dependent generally needs a large scale text-dependent training data set which could be labor and cost expensive, especially for customized new wake-up words. In recent studies, voice conversion systems that can generate high quality synthesized speech of seen and unseen speakers have been proposed. Inspired by those works, we adopt two different voice conversion methods as well as the very simple re-sampling approach to generate new text-dependent speech samples for data augmentation purposes. Experimental results show that the proposed method significantly improves the Equal Error Rare performance from 6.51% to 4.51% in the scenario of limited training data.

Yan Jia, Zexin Cai, Murong Ma et al.

Confusing-words are commonly encountered in real-life keyword spotting applications, which causes severe degradation of performance due to complex spoken terms and various kinds of words that sound similar to the predefined keywords. To enhance the wake word detection system's robustness on such scenarios, we investigate two data augmentation setups for training end-to-end KWS systems. One is involving the synthesized data from a multi-speaker speech synthesis system, and the other augmentation is performed by adding random noise to the acoustic feature. Experimental results show that augmentations help improve the system's robustness. Moreover, by augmenting the training set with the synthetic data generated by the multi-speaker text-to-speech system, we achieve a significant improvement regarding confusing words scenario.

Danwei Cai, Weiqing Wang, Ming Li

In this paper, we propose an iterative framework for self-supervised speaker representation learning based on a deep neural network (DNN). The framework starts with training a self-supervision speaker embedding network by maximizing agreement between different segments within an utterance via a contrastive loss. Taking advantage of DNN's ability to learn from data with label noise, we propose to cluster the speaker embedding obtained from the previous speaker network and use the subsequent class assignments as pseudo labels to train a new DNN. Moreover, we iteratively train the speaker network with pseudo labels generated from the previous step to bootstrap the discriminative power of a DNN. Speaker verification experiments are conducted on the VoxCeleb dataset. The results show that our proposed iterative self-supervised learning framework outperformed previous works using self-supervision. The speaker network after 5 iterations obtains a 61% performance gain over the speaker embedding model trained with contrastive loss.

Yao Shi, Hui Bu, Xin Xu et al.

In this paper, we present AISHELL-3, a large-scale and high-fidelity multi-speaker Mandarin speech corpus which could be used to train multi-speaker Text-to-Speech (TTS) systems. The corpus contains roughly 85 hours of emotion-neutral recordings spoken by 218 native Chinese mandarin speakers. Their auxiliary attributes such as gender, age group and native accents are explicitly marked and provided in the corpus. Accordingly, transcripts in Chinese character-level and pinyin-level are provided along with the recordings. We present a baseline system that uses AISHELL-3 for multi-speaker Madarin speech synthesis. The multi-speaker speech synthesis system is an extension on Tacotron-2 where a speaker verification model and a corresponding loss regarding voice similarity are incorporated as the feedback constraint. We aim to use the presented corpus to build a robust synthesis model that is able to achieve zero-shot voice cloning. The system trained on this dataset also generalizes well on speakers that are never seen in the training process. Objective evaluation results from our experiments show that the proposed multi-speaker synthesis system achieves high voice similarity concerning both speaker embedding similarity and equal error rate measurement. The dataset, baseline system code and generated samples are available online.

Haiwei Wu, Lin Zhang, Lin Yang et al.

This paper introduces our approaches for the Mask and Breathing Sub-Challenge in the Interspeech COMPARE Challenge 2020. For the mask detection task, we train deep convolutional neural networks with filter-bank energies, gender-aware features, and speaker-aware features. Support Vector Machines follows as the back-end classifiers for binary prediction on the extracted deep embeddings. Several data augmentation schemes are used to increase the quantity of training data and improve our models' robustness, including speed perturbation, SpecAugment, and random erasing. For the speech breath monitoring task, we investigate different bottleneck features based on the Bi-LSTM structure. Experimental results show that our proposed methods outperform the baselines and achieve 0.746 PCC and 78.8% UAR on the Breathing and Mask evaluation set, respectively.

Fernando Andreotti, Frank S. Heldt, Basel Abu-Jamous et al.

In this work, we propose a multi-task recurrent neural network with attention mechanism for predicting cardiovascular events from electronic health records (EHRs) at different time horizons. The proposed approach is compared to a standard clinical risk predictor (QRISK) and machine learning alternatives using 5-year data from a NHS Foundation Trust. The proposed model outperforms standard clinical risk scores in predicting stroke (AUC=0.85) and myocardial infarction (AUC=0.89), considering the largest time horizon. Benefit of using an \gls{mt} setting becomes visible for very short time horizons, which results in an AUC increase between 2-6%. Further, we explored the importance of individual features and attention weights in predicting cardiovascular events. Our results indicate that the recurrent neural network approach benefits from the hospital longitudinal information and demonstrates how machine learning techniques can be applied to secondary care.

Murong Ma, Haiwei Wu, Xuyang Wang et al.

In this paper, we propose a deep convolutional neural network-based acoustic word embedding system on code-switching query by example spoken term detection. Different from previous configurations, we combine audio data in two languages for training instead of only using one single language. We transform the acoustic features of keyword templates and searching content to fixed-dimensional vectors and calculate the distances between keyword segments and searching content segments obtained in a sliding manner. An auxiliary variability-invariant loss is also applied to training data within the same word but different speakers. This strategy is used to prevent the extractor from encoding undesired speaker- or accent-related information into the acoustic word embeddings. Experimental results show that our proposed system produces promising searching results in the code-switching test scenario. With the increased number of templates and the employment of variability-invariant loss, the searching performance is further enhanced.

Zexin Cai, Yaogen Yang, Ming Li

Modeling voices for multiple speakers and multiple languages in one text-to-speech system has been a challenge for a long time. This paper presents an extension on Tacotron2 to achieve bilingual multispeaker speech synthesis when there are limited data for each language. We achieve cross-lingual synthesis, including code-switching cases, between English and Mandarin for monolingual speakers. The two languages share the same phonemic representations for input, while the language attribute and the speaker identity are independently controlled by language tokens and speaker embeddings, respectively. In addition, we investigate the model's performance on the cross-lingual synthesis, with and without a bilingual dataset during training. With the bilingual dataset, not only can the model generate high-fidelity speech for all speakers concerning the language they speak, but also can generate accented, yet fluent and intelligible speech for monolingual speakers regarding non-native language. For example, the Mandarin speaker can speak English fluently. Furthermore, the model trained with bilingual dataset is robust for code-switching text-to-speech, as shown in our results and provided samples.{https://caizexin.github.io/mlms-syn-samples/index.html}.

Tingle Li, Qingjian Lin, Yuanyuan Bao et al.

Recently, Convolutional Neural Network (CNN) and Long short-term memory (LSTM) based models have been introduced to deep learning-based target speaker separation. In this paper, we propose an Attention-based neural network (Atss-Net) in the spectrogram domain for the task. It allows the network to compute the correlation between each feature parallelly, and using shallower layers to extract more features, compared with the CNN-LSTM architecture. Experimental results show that our Atss-Net yields better performance than the VoiceFilter, although it only contains half of the parameters. Furthermore, our proposed model also demonstrates promising performance in speech enhancement.

Xiaoyi Qin, Ming Li, Hui Bu et al.

The INTERSPEECH 2020 Far-Field Speaker Verification Challenge (FFSVC 2020) addresses three different research problems under well-defined conditions: far-field text-dependent speaker verification from single microphone array, far-field text-independent speaker verification from single microphone array, and far-field text-dependent speaker verification from distributed microphone arrays. All three tasks pose a cross-channel challenge to the participants. To simulate the real-life scenario, the enrollment utterances are recorded from close-talk cellphone, while the test utterances are recorded from the far-field microphone arrays. In this paper, we describe the database, the challenge, and the baseline system, which is based on a ResNet-based deep speaker network with cosine similarity scoring. For a given utterance, the speaker embeddings of different channels are equally averaged as the final embedding. The baseline system achieves minDCFs of 0.62, 0.66, and 0.64 and EERs of 6.27%, 6.55%, and 7.18% for task 1, task 2, and task 3, respectively.

Zexin Cai, Chuxiong Zhang, Ming Li

High-fidelity speech can be synthesized by end-to-end text-to-speech models in recent years. However, accessing and controlling speech attributes such as speaker identity, prosody, and emotion in a text-to-speech system remains a challenge. This paper presents a system involving feedback constraint for multispeaker speech synthesis. We manage to enhance the knowledge transfer from the speaker verification to the speech synthesis by engaging the speaker verification network. The constraint is taken by an added loss related to the speaker identity, which is centralized to improve the speaker similarity between the synthesized speech and its natural reference audio. The model is trained and evaluated on publicly available datasets. Experimental results, including visualization on speaker embedding space, show significant improvement in terms of speaker identity cloning in the spectrogram level. Synthesized samples are available online for listening. (https://caizexin.github.io/mlspk-syn-samples/index.html)