English
Related papers

Related papers: Speech-Declipping Transformer with Complex Spectro…

200 papers

End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-11-28 Pu Wang , Hugo Van hamme

Time-frequency (TF) domain dual-path models achieve high-fidelity speech separation. While some previous state-of-the-art (SoTA) models rely on RNNs, this reliance means they lack the parallelizability, scalability, and versatility of…

Audio and Speech Processing · Electrical Eng. & Systems 2024-08-08 Kohei Saijo , Gordon Wichern , François G. Germain , Zexu Pan , Jonathan Le Roux

Recently deep neural networks (DNNs) have been used to learn speaker features. However, the quality of the learned features is not sufficiently good, so a complex back-end model, either neural or probabilistic, has to be used to address the…

Sound · Computer Science 2017-05-11 Lantian Li , Yixiang Chen , Ying Shi , Zhiyuan Tang , Dong Wang

Speech enhancement is critical for improving speech intelligibility and quality in various audio devices. In recent years, deep learning-based methods have significantly improved speech enhancement performance, but they often come with a…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-08 Xiang Hao , Chenxiang Ma , Qu Yang , Jibin Wu , Kay Chen Tan

Recently, deep neural networks (DNNs) have been successfully used for speech enhancement, and DNN-based speech enhancement is becoming an attractive research area. While time-frequency masking based on the short-time Fourier transform…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-21 Yuichiro Koyama , Tyler Vuong , Stefan Uhlich , Bhiksha Raj

Recent advances in deep learning have significantly improved multichannel speech enhancement algorithms, yet conventional training loss functions such as the scale-invariant signal-to-distortion ratio (SDR) may fail to preserve fine-grained…

Sound · Computer Science 2025-06-24 Nasser-Eddine Monir , Paul Magron , Romain Serizel

Time delay neural networks (TDNNs) are an effective acoustic model for large vocabulary speech recognition. The strength of the model can be attributed to its ability to effectively model long temporal contexts. However, current TDNN models…

Computation and Language · Computer Science 2018-02-21 Florian Kreyssig , Chao Zhang , Philip Woodland

Despite the rapid progress of automatic speech recognition (ASR) technologies targeting normal speech in recent decades, accurate recognition of dysarthric and elderly speech remains highly challenging tasks to date. Sources of…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-18 Mengzhe Geng , Xurong Xie , Zi Ye , Tianzi Wang , Guinan Li , Shujie Hu , Xunying Liu , Helen Meng

Recent speech enhancement methods based on convolutional neural networks (CNNs) and transformer have been demonstrated to efficaciously capture time-frequency (T-F) information on spectrogram. However, the correlation of each channels of…

Sound · Computer Science 2024-07-16 Jizhen Li , Xinmeng Xu , Weiping Tu , Yuhong Yang , Rong Zhu

Automatic recognition of disordered speech remains a highly challenging task to date. Sources of variability commonly found in normal speech including accent, age or gender, when further compounded with the underlying causes of speech…

Sound · Computer Science 2022-01-20 Mengzhe Geng , Shansong Liu , Jianwei Yu , Xurong Xie , Shoukang Hu , Zi Ye , Zengrui Jin , Xunying Liu , Helen Meng

Speech dereverberation is an important stage in many speech technology applications. Recent work in this area has been dominated by deep neural network models. Temporal convolutional networks (TCNs) are deep learning models that have been…

Sound · Computer Science 2022-07-26 William Ravenscroft , Stefan Goetze , Thomas Hain

This study investigates phase reconstruction for deep learning based monaural talker-independent speaker separation in the short-time Fourier transform (STFT) domain. The key observation is that, for a mixture of two sources, with their…

Sound · Computer Science 2018-11-26 Zhong-Qiu Wang , Ke Tan , DeLiang Wang

Recent studies in deep learning-based speech separation have proven the superiority of time-domain approaches to conventional time-frequency-based methods. Unlike the time-frequency domain approaches, the time-domain separation systems…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-30 Yi Luo , Zhuo Chen , Takuya Yoshioka

Recent high-performance transformer-based speech enhancement models demonstrate that time domain methods could achieve similar performance as time-frequency domain methods. However, time-domain speech enhancement systems typically receive…

Sound · Computer Science 2023-10-31 Junhui Li , Pu Wang , Jialu Li , Xinzhe Wang , Youshan Zhang

Detecting spoofed utterances is a fundamental problem in voice-based biometrics. Spoofing can be performed either by logical accesses like speech synthesis, voice conversion or by physical accesses such as replaying the pre-recorded…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-28 Mari Ganesh Kumar , Suvidha Rupesh Kumar , Saranya M , B. Bharathi , Hema A. Murthy

The wide deployment of speech-based biometric systems usually demands high-performance speaker recognition algorithms. However, most of the prior works for speaker recognition either process the speech in the frequency domain or time…

Sound · Computer Science 2023-03-08 Jiguo Li , Tianzi Zhang , Xiaobin Liu , Lirong Zheng

Transformer-based Spiking Neural Networks (SNNs) suffer from a great performance gap compared to floating-point \mbox{Artificial} Neural Networks (ANNs) due to the binary nature of spike trains. Recent efforts have introduced deep-level…

Neural and Evolutionary Computing · Computer Science 2025-08-12 Zeqi Zheng , Zizheng Zhu , Yingchao Yu , Yanchen Huang , Changze Lv , Junfeng Tang , Zhaofei Yu , Yaochu Jin

In this paper, several works are proposed to address practical challenges for deploying RNN Transducer (RNN-T) based speech recognition system. These challenges are adapting a well-trained RNN-T model to a new domain without collecting the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-20 Rui Zhao , Jian Xue , Jinyu Li , Wenning Wei , Lei He , Yifan Gong

We improve on the popular conformer architecture by replacing the depthwise temporal convolutions with diagonal state space (DSS) models. DSS is a recently introduced variant of linear RNNs obtained by discretizing a linear dynamical system…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-01 George Saon , Ankit Gupta , Xiaodong Cui

We propose a multi-dimensional structured state space (S4) approach to speech enhancement. To better capture the spectral dependencies across the frequency axis, we focus on modifying the multi-dimensional S4 layer with whitening…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-28 Pin-Jui Ku , Chao-Han Huck Yang , Sabato Marco Siniscalchi , Chin-Hui Lee