Helin Wang

Junling Liu, Peilin Zhou, Yining Hua et al.

Recent advancements in large language models (LLMs) have transformed the field of question answering (QA). However, evaluating LLMs in the medical field is challenging due to the lack of standardized and comprehensive datasets. To address this gap, we introduce CMExam, sourced from the Chinese National Medical Licensing Examination. CMExam consists of 60K+ multiple-choice questions for standardized and objective evaluations, as well as solution explanations for model reasoning evaluation in an open-ended manner. For in-depth analyses of LLMs, we invited medical professionals to label five additional question-wise annotations, including disease groups, clinical departments, medical disciplines, areas of competency, and question difficulty levels. Alongside the dataset, we further conducted thorough experiments with representative LLMs and QA algorithms on CMExam. The results show that GPT-4 had the best accuracy of 61.6% and a weighted F1 score of 0.617. These results highlight a great disparity when compared to human accuracy, which stood at 71.6%. For explanation tasks, while LLMs could generate relevant reasoning and demonstrate improved performance after finetuning, they fall short of a desired standard, indicating ample room for improvement. To the best of our knowledge, CMExam is the first Chinese medical exam dataset to provide comprehensive medical annotations. The experiments and findings of LLM evaluation also provide valuable insights into the challenges and potential solutions in developing Chinese medical QA systems and LLM evaluation pipelines. The dataset and relevant code are available at https://github.com/williamliujl/CMExam.

Dongchao Yang, Jianwei Yu, Helin Wang et al.

Generating sound effects that humans want is an important topic. However, there are few studies in this area for sound generation. In this study, we investigate generating sound conditioned on a text prompt and propose a novel text-to-sound generation framework that consists of a text encoder, a Vector Quantized Variational Autoencoder (VQ-VAE), a decoder, and a vocoder. The framework first uses the decoder to transfer the text features extracted from the text encoder to a mel-spectrogram with the help of VQ-VAE, and then the vocoder is used to transform the generated mel-spectrogram into a waveform. We found that the decoder significantly influences the generation performance. Thus, we focus on designing a good decoder in this study. We begin with the traditional autoregressive decoder, which has been proved as a state-of-the-art method in previous sound generation works. However, the AR decoder always predicts the mel-spectrogram tokens one by one in order, which introduces the unidirectional bias and accumulation of errors problems. Moreover, with the AR decoder, the sound generation time increases linearly with the sound duration. To overcome the shortcomings introduced by AR decoders, we propose a non-autoregressive decoder based on the discrete diffusion model, named Diffsound. Specifically, the Diffsound predicts all of the mel-spectrogram tokens in one step and then refines the predicted tokens in the next step, so the best-predicted results can be obtained after several steps. Our experiments show that our proposed Diffsound not only produces better text-to-sound generation results when compared with the AR decoder but also has a faster generation speed, e.g., MOS: 3.56 \textit{v.s} 2.786, and the generation speed is five times faster than the AR decoder.

Bowen Shi, Andros Tjandra, John Hoffman et al.

General audio source separation is a key capability for multimodal AI systems that can perceive and reason about sound. Despite substantial progress in recent years, existing separation models are either domain-specific, designed for fixed categories such as speech or music, or limited in controllability, supporting only a single prompting modality such as text. In this work, we present SAM Audio, a foundation model for general audio separation that unifies text, visual, and temporal span prompting within a single framework. Built on a diffusion transformer architecture, SAM Audio is trained with flow matching on large-scale audio data spanning speech, music, and general sounds, and can flexibly separate target sources described by language, visual masks, or temporal spans. The model achieves state-of-the-art performance across a diverse suite of benchmarks, including general sound, speech, music, and musical instrument separation in both in-the-wild and professionally produced audios, substantially outperforming prior general-purpose and specialized systems. Furthermore, we introduce a new real-world separation benchmark with human-labeled multimodal prompts and a reference-free evaluation model that correlates strongly with human judgment.

Peilin Zhou, Dading Chong, Helin Wang et al.

The past ten years have witnessed the rapid development of text-based intent detection, whose benchmark performances have already been taken to a remarkable level by deep learning techniques. However, automatic speech recognition (ASR) errors are inevitable in real-world applications due to the environment noise, unique speech patterns and etc, leading to sharp performance drop in state-of-the-art text-based intent detection models. Essentially, this phenomenon is caused by the semantic drift brought by ASR errors and most existing works tend to focus on designing new model structures to reduce its impact, which is at the expense of versatility and flexibility. Different from previous one-piece model, in this paper, we propose a novel and agile framework called CR-ID for ASR error robust intent detection with two plug-and-play modules, namely semantic drift calibration module (SDCM) and phonemic refinement module (PRM), which are both model-agnostic and thus could be easily integrated to any existing intent detection models without modifying their structures. Experimental results on SNIPS dataset show that, our proposed CR-ID framework achieves competitive performance and outperform all the baseline methods on ASR outputs, which verifies that CR-ID can effectively alleviate the semantic drift caused by ASR errors.

Jingpu Yang, Helin Wang, Qirui Zhao et al.

Reinforcement Learning (RL), recognized as an efficient learning approach, has achieved remarkable success across multiple fields and applications, including gaming, robotics, and autonomous vehicles. Classical single-agent reinforcement learning grapples with the imbalance of exploration and exploitation as well as limited generalization abilities. This methodology frequently leads to algorithms settling for suboptimal solutions that are tailored only to specific datasets. In this work, our aim is to train agent with efficient learning by decoupling exploration and utilization, so that agent can escaping the conundrum of suboptimal Solutions. In reinforcement learning, the previously imposed pessimistic punitive measures have deprived the model of its exploratory potential, resulting in diminished exploration capabilities. To address this, we have introduced an additional optimistic Actor to enhance the model's exploration ability, while employing a more constrained pessimistic Actor for performance evaluation. The above idea is implemented in the proposed OPARL (Optimistic and Pessimistic Actor Reinforcement Learning) algorithm. This unique amalgamation within the reinforcement learning paradigm fosters a more balanced and efficient approach. It facilitates the optimization of policies that concentrate on high-reward actions via pessimistic exploitation strategies while concurrently ensuring extensive state coverage through optimistic exploration. Empirical and theoretical investigations demonstrate that OPARL enhances agent capabilities in both utilization and exploration. In the most tasks of DMControl benchmark and Mujoco environment, OPARL performed better than state-of-the-art methods. Our code has released on https://github.com/yydsok/OPARL

Zhongjie Ye, Helin Wang, Dongchao Yang et al.

Automated audio captioning (AAC) has developed rapidly in recent years, involving acoustic signal processing and natural language processing to generate human-readable sentences for audio clips. The current models are generally based on the neural encoder-decoder architecture, and their decoder mainly uses acoustic information that is extracted from the CNN-based encoder. However, they have ignored semantic information that could help the AAC model to generate meaningful descriptions. This paper proposes a novel approach for automated audio captioning based on incorporating semantic and acoustic information. Specifically, our audio captioning model consists of two sub-modules. (1) The pre-trained keyword encoder utilizes pre-trained ResNet38 to initialize its parameters, and then it is trained by extracted keywords as labels. (2) The multi-modal attention decoder adopts an LSTM-based decoder that contains semantic and acoustic attention modules. Experiments demonstrate that our proposed model achieves state-of-the-art performance on the Clotho dataset. Our code can be found at https://github.com/WangHelin1997/DCASE2021_Task6_PKU

Chen Chen, Yuchen Hu, Siyin Wang et al.

An ideal multimodal agent should be aware of the quality of its input modalities. Recent advances have enabled large language models (LLMs) to incorporate auditory systems for handling various speech-related tasks. However, most audio LLMs remain unaware of the quality of the speech they process. This limitation arises because speech quality evaluation is typically excluded from multi-task training due to the lack of suitable datasets. To address this, we introduce the first natural language-based speech evaluation corpus, generated from authentic human ratings. In addition to the overall Mean Opinion Score (MOS), this corpus offers detailed analysis across multiple dimensions and identifies causes of quality degradation. It also enables descriptive comparisons between two speech samples (A/B tests) with human-like judgment. Leveraging this corpus, we propose an alignment approach with LLM distillation (ALLD) to guide the audio LLM in extracting relevant information from raw speech and generating meaningful responses. Experimental results demonstrate that ALLD outperforms the previous state-of-the-art regression model in MOS prediction, with a mean square error of 0.17 and an A/B test accuracy of 98.6%. Additionally, the generated responses achieve BLEU scores of 25.8 and 30.2 on two tasks, surpassing the capabilities of task-specific models. This work advances the comprehensive perception of speech signals by audio LLMs, contributing to the development of real-world auditory and sensory intelligent agents.

Yen-Ju Lu, Kunxiao Gao, Mingrui Liang et al.

Recent audio language models can follow long conversations. However, research on emotion-aware or spoken dialogue summarization is constrained by the lack of data that links speech, summaries, and paralinguistic cues. We introduce Spoken DialogSum, the first corpus aligning raw conversational audio with factual summaries, emotion-rich summaries, and utterance-level labels for speaker age, gender, and emotion. The dataset is built in two stages: first, an LLM rewrites DialogSum scripts with Switchboard-style fillers and back-channels, then tags each utterance with emotion, pitch, and speaking rate. Second, an expressive TTS engine synthesizes speech from the tagged scripts, aligned with paralinguistic labels. Spoken DialogSum comprises 13,460 emotion-diverse dialogues, each paired with both a factual and an emotion-focused summary. We release an online demo at https://fatfat-emosum.github.io/EmoDialog-Sum-Audio-Samples/, with plans to release the full dataset in the near future. Baselines show that an Audio-LLM raises emotional-summary ROUGE-L by 28% relative to a cascaded ASR-LLM system, confirming the value of end-to-end speech modeling.

Jiarui Hai, Helin Wang, Weizhe Guo et al.

Despite recent progress in large-scale sound event detection (SED) systems capable of handling hundreds of sound classes, existing multi-class classification frameworks remain fundamentally limited. They cannot process free-text sound queries, which enable more flexible and user-friendly interaction, and they lack zero-shot capabilities and offer poor few-shot adaptability. Although text-query-based separation methods have been explored, they primarily focus on source separation and are ill-suited for SED tasks that require precise temporal localization and efficient detection across large and diverse sound vocabularies. In this paper, we propose FlexSED, an open-vocabulary sound event detection system. FlexSED builds on a pretrained audio SSL model and the CLAP text encoder, introducing an encoder-decoder composition and an adaptive fusion strategy to enable effective continuous training from pretrained weights. To ensure robust supervision, it also employs large language models (LLMs) to assist in event query selection during training, addressing challenges related to missing labels. As a result, FlexSED achieves superior performance compared to vanilla SED models on AudioSet-Strong, while demonstrating strong zero-shot and few-shot capabilities. We release the code and pretrained models to support future research and applications based on FlexSED.

Junhyeok Lee, Helin Wang, Yaohan Guan et al.

We introduce MaskVCT, a zero-shot voice conversion (VC) model that offers multi-factor controllability through multiple classifier-free guidances (CFGs). While previous VC models rely on a fixed conditioning scheme, MaskVCT integrates diverse conditions in a single model. To further enhance robustness and control, the model can leverage continuous or quantized linguistic features to enhance intellgibility and speaker similarity, and can use or omit pitch contour to control prosody. These choices allow users to seamlessly balance speaker identity, linguistic content, and prosodic factors in a zero-shot VC setting. Extensive experiments demonstrate that MaskVCT achieves the best target speaker and accent similarities while obtaining competitive word and character error rates compared to existing baselines. Audio samples are available at https://maskvct.github.io/.

Chen Chen, Yuchen Hu, Wen Wu et al.

In recent years, text-to-speech (TTS) technology has witnessed impressive advancements, particularly with large-scale training datasets, showcasing human-level speech quality and impressive zero-shot capabilities on unseen speakers. However, despite human subjective evaluations, such as the mean opinion score (MOS), remaining the gold standard for assessing the quality of synthetic speech, even state-of-the-art TTS approaches have kept human feedback isolated from training that resulted in mismatched training objectives and evaluation metrics. In this work, we investigate a novel topic of integrating subjective human evaluation into the TTS training loop. Inspired by the recent success of reinforcement learning from human feedback, we propose a comprehensive sampling-annotating-learning framework tailored to TTS optimization, namely uncertainty-aware optimization (UNO). Specifically, UNO eliminates the need for a reward model or preference data by directly maximizing the utility of speech generations while considering the uncertainty that lies in the inherent variability in subjective human speech perception and evaluations. Experimental results of both subjective and objective evaluations demonstrate that UNO considerably improves the zero-shot performance of TTS models in terms of MOS, word error rate, and speaker similarity. Additionally, we present a remarkable ability of UNO that it can adapt to the desired speaking style in emotional TTS seamlessly and flexibly.

Dongchao Yang, Helin Wang, Yuexian Zou et al.

Human beings can perceive a target sound type from a multi-source mixture signal by the selective auditory attention, however, such functionality was hardly ever explored in machine hearing. This paper addresses the target sound detection (TSD) task, which aims to detect the target sound signal from a mixture audio when a target sound's reference audio is given. We present a novel target sound detection network (TSDNet) which consists of two main parts: A conditional network which aims at generating a sound-discriminative conditional embedding vector representing the target sound, and a detection network which takes both the mixture audio and the conditional embedding vector as inputs and produces the detection result of the target sound. These two networks can be jointly optimized with a multi-task learning approach to further improve the performance. In addition, we study both strong-supervised and weakly-supervised strategies to train TSDNet and propose a data augmentation method by mixing two samples. To facilitate this research, we build a target sound detection dataset (\textit{i.e.} URBAN-TSD) based on URBAN-SED and UrbanSound8K datasets, and experimental results indicate our method could get the segment-based F scores of 76.3$\%$ and 56.8$\%$ on the strongly-labelled and weakly-labelled data respectively.

Dongchao Yang, Helin Wang, Yuexian Zou et al.

Although prototypical network (ProtoNet) has proved to be an effective method for few-shot sound event detection, two problems still exist. Firstly, the small-scaled support set is insufficient so that the class prototypes may not represent the class center accurately. Secondly, the feature extractor is task-agnostic (or class-agnostic): the feature extractor is trained with base-class data and directly applied to unseen-class data. To address these issues, we present a novel mutual learning framework with transductive learning, which aims at iteratively updating the class prototypes and feature extractor. More specifically, we propose to update class prototypes with transductive inference to make the class prototypes as close to the true class center as possible. To make the feature extractor to be task-specific, we propose to use the updated class prototypes to fine-tune the feature extractor. After that, a fine-tuned feature extractor further helps produce better class prototypes. Our method achieves the F-score of 38.4$\%$ on the DCASE 2021 Task 5 evaluation set, which won the first place in the few-shot bioacoustic event detection task of Detection and Classification of Acoustic Scenes and Events (DCASE) 2021 Challenge.

Zhiqi Huang, Fenglin Liu, Xian Wu et al.

While Machine Comprehension (MC) has attracted extensive research interests in recent years, existing approaches mainly belong to the category of Machine Reading Comprehension task which mines textual inputs (paragraphs and questions) to predict the answers (choices or text spans). However, there are a lot of MC tasks that accept audio input in addition to the textual input, e.g. English listening comprehension test. In this paper, we target the problem of Audio-Oriented Multimodal Machine Comprehension, and its goal is to answer questions based on the given audio and textual information. To solve this problem, we propose a Dynamic Inter- and Intra-modality Attention (DIIA) model to effectively fuse the two modalities (audio and textual). DIIA can work as an independent component and thus be easily integrated into existing MC models. Moreover, we further develop a Multimodal Knowledge Distillation (MKD) module to enable our multimodal MC model to accurately predict the answers based only on either the text or the audio. As a result, the proposed approach can handle various tasks including: Audio-Oriented Multimodal Machine Comprehension, Machine Reading Comprehension and Machine Listening Comprehension, in a single model, making fair comparisons possible between our model and the existing unimodal MC models. Experimental results and analysis prove the effectiveness of the proposed approaches. First, the proposed DIIA boosts the baseline models by up to 21.08% in terms of accuracy; Second, under the unimodal scenarios, the MKD module allows our multimodal MC model to significantly outperform the unimodal models by up to 18.87%, which are trained and tested with only audio or textual data.

Dongchao Yang, Helin Wang, Yuexian Zou

It is well known that the mismatch between training (source) and test (target) data distribution will significantly decrease the performance of acoustic scene classification (ASC) systems. To address this issue, domain adaptation (DA) is one solution and many unsupervised DA methods have been proposed. These methods focus on a scenario of single source domain to single target domain. However, we will face such problem that test data comes from multiple target domains. This problem can be addressed by producing one model per target domain, but this solution is too costly. In this paper, we propose a novel unsupervised multi-target domain adaption (MTDA) method for ASC, which can adapt to multiple target domains simultaneously and make use of the underlying relation among multiple domains. Specifically, our approach combines traditional adversarial adaptation with two novel discriminator tasks that learns a common subspace shared by all domains. Furthermore, we propose to divide the target domain into the easy-to-adapt and hard-to-adapt domain, which enables the system to pay more attention to hard-to-adapt domain in training. The experimental results on the DCASE 2020 Task 1-A dataset and the DCASE 2019 Task 1-B dataset show that our proposed method significantly outperforms the previous unsupervised DA methods.

Jinchuan Tian, Rongzhi Gu, Helin Wang et al.

Transformer-based self-supervised models are trained as feature extractors and have empowered many downstream speech tasks to achieve state-of-the-art performance. However, both the training and inference process of these models may encounter prohibitively high computational cost and large parameter budget. Although Parameter Sharing Strategy (PSS) proposed in ALBERT paves the way for parameter reduction, the computation required remains the same. Interestingly, we found in experiments that distributions of feature embeddings from different Transformer layers are similar when PSS is integrated: a property termed as Layer Consistency (LC) in this paper. Given this similarity of feature distributions, we assume that feature embeddings from different layers would have similar representing power. In this work, Layer Consistency enables us to adopt Transformer-based models in a more efficient manner: the number of Conformer layers in each training iteration could be uniformly sampled and Shallow Layer Inference (SLI) could be applied to reduce the number of layers in inference stage. In experiments, our models are trained with LibriSpeech dataset and then evaluated on both phone classification and Speech Recognition tasks. We experimentally achieve 7.8X parameter reduction, 41.9% training speedup and 37.7% inference speedup while maintaining comparable performance with conventional BERT-like self-supervised methods.

Helin Wang, Yuexian Zou, Wenwu Wang

In this paper, we present SpecAugment++, a novel data augmentation method for deep neural networks based acoustic scene classification (ASC). Different from other popular data augmentation methods such as SpecAugment and mixup that only work on the input space, SpecAugment++ is applied to both the input space and the hidden space of the deep neural networks to enhance the input and the intermediate feature representations. For an intermediate hidden state, the augmentation techniques consist of masking blocks of frequency channels and masking blocks of time frames, which improve generalization by enabling a model to attend not only to the most discriminative parts of the feature, but also the entire parts. Apart from using zeros for masking, we also examine two approaches for masking based on the use of other samples within the minibatch, which helps introduce noises to the networks to make them more discriminative for classification. The experimental results on the DCASE 2018 Task1 dataset and DCASE 2019 Task1 dataset show that our proposed method can obtain 3.6% and 4.7% accuracy gains over a strong baseline without augmentation (i.e. CP-ResNet) respectively, and outperforms other previous data augmentation methods.

Helin Wang, Bo Wu, Lianwu Chen et al.

In this paper, we exploit the effective way to leverage contextual information to improve the speech dereverberation performance in real-world reverberant environments. We propose a temporal-contextual attention approach on the deep neural network (DNN) for environment-aware speech dereverberation, which can adaptively attend to the contextual information. More specifically, a FullBand based Temporal Attention approach (FTA) is proposed, which models the correlations between the fullband information of the context frames. In addition, considering the difference between the attenuation of high frequency bands and low frequency bands (high frequency bands attenuate faster than low frequency bands) in the room impulse response (RIR), we also propose a SubBand based Temporal Attention approach (STA). In order to guide the network to be more aware of the reverberant environments, we jointly optimize the dereverberation network and the reverberation time (RT60) estimator in a multi-task manner. Our experimental results indicate that the proposed method outperforms our previously proposed reverberation-time-aware DNN and the learned attention weights are fully physical consistent. We also report a preliminary yet promising dereverberation and recognition experiment on real test data.

Helin Wang, Yuexian Zou, Wenwu Wang

Weakly labelled audio tagging aims to predict the classes of sound events within an audio clip, where the onset and offset times of the sound events are not provided. Previous works have used the multiple instance learning (MIL) framework, and exploited the information of the whole audio clip by MIL pooling functions. However, the detailed information of sound events such as their durations may not be considered under this framework. To address this issue, we propose a novel two-stream framework for audio tagging by exploiting the global and local information of sound events. The global stream aims to analyze the whole audio clip in order to capture the local clips that need to be attended using a class-wise selection module. These clips are then fed to the local stream to exploit the detailed information for a better decision. Experimental results on the AudioSet show that our proposed method can significantly improve the performance of audio tagging under different baseline network architectures.

Helin Wang, Yuexian Zou, Dading Chong

Recently, convolutional neural networks (CNN) have achieved the state-of-the-art performance in acoustic scene classification (ASC) task. The audio data is often transformed into two-dimensional spectrogram representations, which are then fed to the neural networks. In this paper, we study the problem of efficiently taking advantage of different spectrogram representations through discriminative processing strategies. There are two main contributions. The first contribution is exploring the impact of the combination of multiple spectrogram representations at different stages, which provides a meaningful reference for the effective spectrogram fusion. The second contribution is that the processing strategies in multiple frequency bands and multiple temporal frames are proposed to make fully use of a single spectrogram representation. The proposed spectrogram processing strategies can be easily transferred to any network structures. The experiments are carried out on the DCASE 2020 Task1 datasets, and the results show that our method could achieve the accuracy of 81.8% (official baseline: 54.1%) and 92.1% (official baseline: 87.3%) on the officially provided fold 1 evaluation dataset of Task1A and Task1B, respectively.

Helin Wang, Yuexian Zou, Dading Chong et al.

Convolutional neural networks (CNN) are one of the best-performing neural network architectures for environmental sound classification (ESC). Recently, temporal attention mechanisms have been used in CNN to capture the useful information from the relevant time frames for audio classification, especially for weakly labelled data where the onset and offset times of the sound events are not applied. In these methods, however, the inherent spectral characteristics and variations are not explicitly exploited when obtaining the deep features. In this paper, we propose a novel parallel temporal-spectral attention mechanism for CNN to learn discriminative sound representations, which enhances the temporal and spectral features by capturing the importance of different time frames and frequency bands. Parallel branches are constructed to allow temporal attention and spectral attention to be applied respectively in order to mitigate interference from the segments without the presence of sound events. The experiments on three environmental sound classification (ESC) datasets and two acoustic scene classification (ASC) datasets show that our method improves the classification performance and also exhibits robustness to noise.