82 accepted papers
The ICASSP 2026 URGENT Challenge advances the series by focusing on universal speech enhancement (SE) systems that handle diverse distortions, domains, and input conditions. This overview paper details the challenge's motivation, task definitions, datasets, baseline systems, evaluation protocols, an…
Speech enhancement (SE) improves degraded speech's quality, with generative models like flow matching gaining attention for their outstanding perceptual quality. However, the flow-based model requires multiple numbers of function evaluations (NFEs) to achieve stable and satisfactory performance, lea…
Speech separation (SS) has advanced significantly with neural network-based methods, showing improved performance on signal-level metrics. However, these methods often struggle to maintain speech intelligibility in the separated signals, which can negatively affect the performance of downstream task…
Sound separation (SS) and target sound extraction (TSE) are fundamental techniques for addressing complex acoustic scenarios. While existing SS methods struggle with determining the unknown number of sound sources, TSE approaches require precisely specified clues to achieve optimal performance. This
The acoustic background plays a crucial role in natural conversation. It provides context and helps listeners understand the environment, but a strong background makes it difficult for listeners to understand spoken words. The appropriate handling of these backgrounds is situation-dependent: Althoug…
Recent advancements in speech enhancement (SE) techniques have greatly improved speech clarity and intelligibility in challenging acoustic environments. However, integrating SE into automatic speech recognition (ASR) systems often results in performance degradation due to artifacts introduced during…
Generating natural-sounding, multi-speaker dialogue is crucial for applications such as podcast creation, virtual agents, and multimedia content generation. However, existing systems struggle to maintain speaker consistency, model overlapping speech, and synthesize coherent conversations efficiently…
The goal of the acoustic scene classification (ASC) task is to classify recordings into one of the predefined acoustic scene classes. However, in real-world scenarios, ASC systems often encounter challenges such as recording device mismatch, low-complexity constraints, and the limited availability o…
Pruning is a widely used technique to compress large language models (LLMs) by removing unimportant weights, but it often suffers from significant performance degradation—especially under semi-structured sparsity constraints. Existing pruning methods primarily focus on estimating the importance of i…
Large-scale Seq2Seq speech models like Whisper excel in speech recognition but are limited by their high computational demands, making them difficult to be deployed on resource-constrained devices. This paper introduces a novel and efficient pruning method for compressing these models without retrai…
Speaker diarization is typically considered as a discriminative task, using discriminative approaches to produce fixed diarization results. In this paper, we explore for the first time the use of neural network-based generative methods for speaker diarization. We implement a Flow-Matching (FM) based…
Advances in speech synthesis technologies, like text-to-speech (TTS) and voice conversion (VC), have made detecting deepfake speech increasingly challenging. Spoofing countermeasures often struggle to generalize effectively, particularly when faced with unseen attacks. To address this, we propose a…
Recently, "textless" speech language models (SLMs) based on speech units have made huge progress in generating naturalistic speech, including non-verbal vocalizations. However, the generated speech samples often lack semantic coherence. In this paper, we propose SLM and LLM Integration for spontaneo…
Simultaneous Speech Translation (SimulST) enables real-time cross-lingual communication by jointly optimizing speech recognition and machine translation under strict latency constraints. Existing systems struggle to balance translation quality, latency, and semantic coherence, particularly in multil…
As speech generation technology advances, the risk of misuse through deepfake audio has become a pressing concern, which underscores the critical need for robust detection systems. However, many existing speech deepfake datasets are limited in scale and diversity, making it challenging to train mode…
Recent advancements in zero-shot text-to-speech (TTS) modeling have led to significant strides in generating high-fidelity and diverse speech. However, dialogue generation, along with achieving human-like naturalness in speech, continues to be a challenge. In this paper, we introduce CoVoMix: Conver…
Machine anomalous sound detection is a useful technique for various applications, but it often suffers from poor generalization due to the challenges of data collection and complex acoustic environment. To address this issue, we propose a robust machine anomalous sound detection model that leverages…
Target speech extraction (TSE) is a task aiming at isolating the speech of a specific target speaker from an audio mixture, with the help of an auxiliary recording of that target speaker. Most existing TSE methods employ discrimination-based models to estimate the target speaker’s proportion in the…
Building a single universal speech enhancement (SE) system that can handle arbitrary input is a demanded but underexplored research topic. Towards this ultimate goal, one direction is to build a single model that handles diverse audio duration, sampling frequencies, and microphone variations in nois…
Music editing primarily entails the modification of instrument tracks or remixing in the whole, which offers a novel reinterpretation of the original piece through a series of operations. These music processing methods hold immense potential across various applications but demand substantial experti…
Current speaker recognition systems primarily rely on supervised approaches, constrained by the scale of labeled datasets. To boost the system performance, researchers leverage large pretrained models such as WavLM to transfer learned high-level features to the downstream speaker recognition task. H…
Various Large Language Models (LLMs) from the Generative Pretrained Transformer (GPT) family have achieved outstanding performances in a wide range of text generation tasks. However, the enormous model sizes have hindered their practical use in real-world applications due to high inference latency.…
We introduce a novel task named ‘target speech diarization’, which seeks to determine ‘when target event occurred’ within an audio signal. We devise a neural architecture called Prompt-driven Target Speech Diarization (PTSD), that works with diverse prompts that specify the target speech events of i…
Speaker verification encounters significant challenges when confronted with diverse domain data, often resulting in performance degradation due to domain mismatch. To enhance performance in cross-domain scenarios, we introduce the Domain Adapter, an adaptable module designed for specific domains. Th…
There is a rising interest and trend in research towards directly translating speech from one language to another, known as end-to-end speech-to-speech translation. However, most end-to-end models struggle to outperform cascade models, i.e., a pipeline framework by concatenating speech recognition,…
Large margin fine-tuning (LMFT) is an effective strategy to improve the speaker verification system’s performance and is widely used in speaker verification challenge systems. Because the large margin in the loss function could make the training task too difficult, people usually use longer training…
Code-switching speech refers to a means of expression by mixing two or more languages within a single utterance. Automatic Speech Recognition (ASR) with End-to-End (E2E) modeling for such speech can be a challenging task due to the lack of data. In this study, we investigate text generation and inje…
Joint speech-language training is challenging due to the large demand for training data and GPU consumption, as well as the modality gap between speech and language. We present ComSL, a speech-language model built atop a composite architecture of public pre-trained speech-only and language-only mode…
The mismatch between close-set training and open-set testing usually leads to significant performance degradation for speaker verification task. For existing loss functions, metric learning-based objectives depend strongly on searching effective pairs which might hinder further improvements. And pop…
End-to-end automatic speech recognition (ASR) systems have gained popularity given their simplified architecture and promising results. However, text-only domain adaptation remains a big challenge for E2E systems. Text-to-speech (TTS) based approaches fine-tune ASR models by synthesized speech with…
Self-supervised learning (SSL) has attracted widespread research interest since many successful SSL approaches such as wav2vec 2.0 and Hidden-unit BERT (HuBERT) have achieved promising results on speech-related tasks such as automatic speech recognition (ASR). However, few works have been conducted…
Adapting End-to-End (E2E) models to unseen domains is still a big challenge since training E2E models requires lots of paired audio and text training data. We propose a novel domain adaptation framework for the E2E model, which only uses the text of the target domain. Moreover, the proposed methods…
Traditional automatic speech recognition (ASR) systems usually focus on individual utterances, without considering long-form speech with useful historical information, which is more practical in real scenarios. Simply attending longer transcription history for a vanilla neural transducer model shows…
This paper presents the design and implementation of our system for Track 1 of the Multi-modal Information based Speech Processing (MISP) 2022 Challenge. We design an end-to-end transformer-based multi-talker system. The transformer backbone is well-suited to capture long-term features, which is cru…
In online speech separation, there is a trade-off between inherent latency and speech separation performance. When processing the current input audio, looking ahead to more future context usually brings better speech separation performance but increases the algorithm latency, and vice versa. In the…
Audio-visual speech recognition (AVSR) takes advantage of noise-invariant visual information to improve the robustness of automatic speech recognition (ASR) systems. While previous works mainly focused on the clean condition, we believe the visual modality is more effective in noisy environments. Th…
Automatic target sound extraction (TSE) is a machine learning approach to mimic the human auditory perception capability of attending to a sound source of interest from a mixture of sources. It often uses a model conditioned on a fixed form of target sound clues, such as a sound class label, which l…
Speaker modeling is essential for many related tasks, such as speaker recognition and speaker diarization. The dominant modeling approach is fixed-dimensional vector representation, i.e., speaker embedding. This paper introduces a research and production oriented speaker embedding learning toolkit,…
Automatic speech recognition (ASR) has suffered great performance degradation when facing low-resource languages with limited training data. In this work, we propose a series of training strategies to exploring more effective data utilization for low-resource speech recognition. In low-resource scen…
The speech representations learned from large-scale unlabeled data have shown better generalizability than those from supervised learning and thus attract a lot of interest to be applied for various downstream tasks. In this paper, we explore the limits of speech representations learned by different…
Transformer based on self attention mechanism has demonstrated its state-of-the-art performance in most natural language processing (NLP) tasks, but it’s not very competitive when applied for speaker verification in previous works. Generally, speaker identity is mostly reflected by the relationship…
Convolution and self-attention based neural networks have both obtained excellent performance in automatic speaker verification. However, the convolution model often lacks the ability of long-term dependency modeling due to the limitation of receptive field, while the self-attention model is insuffi…
The advances in attention-based encoder-decoder (AED) networks have brought great progress to end-to-end (E2E) automatic speech recognition (ASR). One way to further improve the performance of AED-based E2E ASR is to introduce an extra text encoder for leveraging extensive text data and thus capture…
Punctuation prediction is essential for automatic speech recognition (ASR). Although many works have been proposed for punctuation prediction, the on-device scenarios are rarely discussed with an end-to-end ASR. The punctuation prediction task is often treated as a post-processing of ASR outputs, bu…
As the most widely used technique, deep speaker embedding learning has become predominant in speaker verification task recently. Very large neural networks such as ECAPA-TDNN and ResNet can achieve the state-of-the-art performance. However, large models are computationally unfriendly in general, whi…
Continuous speech separation for meeting pre-processing has recently become a focused research topic. Compared to the data in utterance-level speech separation, the meeting-style audio stream lasts longer, has an uncertain number of speakers. We adopt the time-domain speech separation method and the…
The ICASSP 2022 Multi-channel Multi-party Meeting Transcription Grand Challenge (M2MeT) focuses on one of the most valuable and the most challenging scenarios of speech technologies. The M2MeT challenge has particularly set up two tracks, speaker diarization (track 1) and multi-speaker automatic spe…
This paper describes the SJTU system for ICASSP Multi-modal Information based Speech Processing Challenge (MISP) 2021. To solve the speech recognition problem in real complex environments where time-synchronized near- and far-field signals are available for training an enhancement frontend. We build…
Incorporating visual information is a promising approach to improve the performance of speech separation. Many related works have been conducted and provide inspiring results. However, low quality videos appear commonly in real scenarios, which may significantly degrade the performance of normal aud…
This paper describes the AISpeech-SJTU ASR system for the Interspeech-2020 Accented English Speech Recognition Challenge (AESRC). This task is challenging due to the diversity of pronunciation accuracy, intonation speed and pronunciation of some syllables. All participants were restricted to develop…
This paper describes the AISpeech-SJTU system for the accent identification track of the Interspeech-2020 Accented English Speech Recognition Challenge. In this challenge track, only 160-hour accented English data collected from 8 countries and the auxiliary Librispeech dataset are provided for trai…
Time-domain training criteria have proven to be very effective for the separation of single-channel non-reverberant speech mixtures. Likewise, mask-based beamforming has shown impressive performance in multi-channel reverberant speech enhancement and source separation. Here, we propose to combine ne…
The continuous speech separation (CSS) is a task to separate the speech sources from a long, partially overlapped recording, which involves a varying number of speakers. A straightforward extension of conventional utterance-level speech separation to the CSS task is to segment the long recording wit…
Recently, the end-to-end approach has been successfully applied to multi-speaker speech separation and recognition in both singlechannel and multichannel conditions. However, severe performance degradation is still observed in the reverberant and noisy scenarios, and there is still a large performan…
Large performance degradation is often observed for speaker verification systems when applied to a new domain dataset. Given an unlabeled target-domain dataset, unsupervised domain adaptation (UDA) methods, which usually leverage adversarial training strategies, are commonly used to bridge the perfo…
Text-dependent speaker verification systems trained on large amount of labelled data exhibit remarkable performance. However, collecting the speech from a lot of speakers with target transcript is a lengthy and expensive process. In this work, we propose a synthesis based data augmentation method (S…
The variety of accents has posed a big challenge to speech recognition. The Accented English Speech Recognition Challenge (AESRC2020) is designed for providing a common testbed and promoting accent-related research. Two tracks are set in the challenge – English accent recognition (track 1) and accen…
Although great progress has been made on automatic speech recognition (ASR) systems, children’s speech recognition still remains a challenging task. General ASR systems for children’s speech suffer from the lack of corpora and mismatch between children’s and adults’ speech. Efforts have been made to…
Data augmentation is commonly used to help build a robust speaker verification system, especially in limited-resource case. However, conventional data augmentation methods usually focus on the diversity of acoustic environment, leaving the lexicon variation neglected. For text dependent speaker veri…
Using deep neural network to extract speaker embedding has significantly improved the speaker verification task. However, such embeddings are still vulnerable to channel variability. Previous works have used adversarial training to suppress channel information to extract channel-invariant embedding…
Previous work shows that audio-visual fusion is a practical approach to deal with the speech separation task in the cocktail party problem. In this paper, we explore a better strategy to utilize visual representations with the attention mechanism. Compared to the previous baseline only using one vis…
Recently, fully recurrent neural network (RNN) based end-to-end models have been proven to be effective for multi-speaker speech recognition in both the single-channel and multi-channel scenarios. In this work, we explore the use of Transformer models for these tasks by focusing on two aspects. Firs…
Text mismatch between pre-collected data, either training data or enrollment data, and the actual test data can significantly hurt text-dependent speaker verification (SV) system performance. Although this problem can be solved by carefully collecting data with the target speech content, such data c…
Recently, end-to-end models have become a popular approach as an alternative to traditional hybrid models in automatic speech recognition (ASR). The multi-speaker speech separation and recognition task is a central task in cocktail party problem. In this paper, we present a state-of-the-art monaural…
Deep speaker embedding learning is an effective method for speaker identity modelling. Very deep models such as ResNet can achieve remarkable results but are usually too computationally expensive for real applications with limited resources. On the other hand, simply reducing model size is likely to…
In this paper, we extend our previous work on direct recognition of single-channel multi-talker mixed speech using permutation invariant training (PIT). We propose to adapt the PIT models with auxiliary features such as pitch and i-vector, and to exploit the gender information with multi-task learni…
Deep neural network (DNN) has achieved the state-of-the-art performance in automatic speech recognition (ASR). However, the meaning of parameters and neurons are hard to be interpreted in DNNs, which makes the regularizations and adaptation of DNNs difficult. In this work, we aim to do effective and…
Recognizing the identities of multiple talkers via their overlapped speech is a challenging task, it is also one main difficulty for the “cocktail party problem”. In this paper, a novel dilated convolutional neural network with a focal KL-divergence loss function is proposed to tackle this problem.…
Data augmentation is an effective method to increase the size of training data and reduce the mismatch between training and testing for noise robust speech recognition. Different from the traditional approaches by directly adding noise to the original waveform, in this work we utilize generative adv…
Factor analysis based i-vector has been the state-of-the-art method for speaker verification. Recently, researchers propose to build DNN based end-to-end speaker verification systems and achieve comparable performance with <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.…
This paper proposes a framework that combines teacher-student training and permutation invariant training (PIT) for single-channel multi-talker speech recognition. In contrast to most of conventional teacher-student training methods that aim at compressing the model, the proposed method distills kno…
Although great progress has been made in automatic speech recognition (ASR), significant performance degradation still exists in noisy environments. Based on our previous introduced very deep CNNs, this paper further integrates residual learning to evaluate very deep convolutional residual network (…
Recently the mask-based beamforming approach received tremendous interest and is widely studied for multi-channel noise robust automatic speech recognition (ASR). Among the known mask estimation models, the neural network based mask estimation approach has received the most attention, resulting in a…
Albeit recent progress in speaker verification generates powerful models, malicious attacks in the form of spoofed speech, are generally not coped with. Recent results in ASVSpoof2015 and BTAS2016 challenges indicate that spoof-aware features are a possible solution to this problem. Most successful…
Far-field speech recognition is an important yet challenging task due to low signal to noise ratio. In this paper, three novel deep neural network architectures are explored to improve the far-field speech recognition accuracy by exploiting the parallel far-field and close-talk recordings. All three…
Automatic segmentation is a crucial initial processing step for processing multi-genre broadcast (MGB) audio. It is very challenging since the data exhibits a wide range of both speech types and background conditions with many types of non-speech audio. This paper describes a segmentation system for…
Although great progress has been made in automatic speech recognition (ASR), significant performance degradation still exists in distant talking scenarios due to significantly lower signal power. In this paper, a novel adaptation framework, named integrated adaptation with multi-factor joint-learnin…
Deep neural networks (DNNs) for acoustic modeling have been shown to provide impressive results on many state-of-the-art automatic speech recognition (ASR) applications. However, DNN performance degrades due to mismatches in training and testing conditions and thus adaptation is necessary. In this p…
Long Short-Term Memory (LSTM) is a particular type of recurrent neural network (RNN) that can model long term temporal dynamics. Recently it has been shown that LSTM-RNNs can achieve higher recognition accuracy than deep feed-forword neural networks (DNNs) in acoustic modelling. However, speaker ada…
Vector Taylor Series (VTS) based model compensation approach has been successfully applied to various robust speech recognition tasks. In this paper, we propose a novel method of variable transformation to calculate the static statistics. In addition, we provide a detailed explanation of VTS and ran…
Although context-dependent DNN-HMM systems have achieved significant improvements over GMM-HMM systems, there still exists big performance degradation if the acoustic condition of the test data mismatches that of the training data. Hence, adaptation and adaptive training of DNN are of great research…
Due to effective word context encoding and long-term context preserving, recurrent neural network language model (RNNLM) has attracted great interest by showing better performance over back-off n-gram models and feed-forward neural network language models (FNNLM). However, it still has the difficult…