English
Related papers

Related papers: UniEnc-CASSNAT: An Encoder-only Non-autoregressive…

200 papers

In this paper, we propose an open source, production first, and production ready speech recognition toolkit called WeNet in which a new two-pass approach is implemented to unify streaming and non-streaming end-to-end (E2E) speech…

Sound · Computer Science 2021-12-30 Zhuoyuan Yao , Di Wu , Xiong Wang , Binbin Zhang , Fan Yu , Chao Yang , Zhendong Peng , Xiaoyu Chen , Lei Xie , Xin Lei

We present Hybrid-Autoregressive INference TrANsducers (HAINAN), a novel architecture for speech recognition that extends the Token-and-Duration Transducer (TDT) model. Trained with randomly masked predictor network outputs, HAINAN supports…

Machine Learning · Computer Science 2025-05-06 Hainan Xu , Travis M. Bartley , Vladimir Bataev , Boris Ginsburg

Thanks to the rise of deep learning and the availability of large-scale audio-visual databases, recent advances have been achieved in Visual Speech Recognition (VSR). Similar to other speech processing tasks, these end-to-end VSR systems…

Computer Vision and Pattern Recognition · Computer Science 2024-02-21 David Gimeno-Gómez , Carlos-D. Martínez-Hinarejos

Automatic Speech Recognition (ASR) in conversational settings presents unique challenges, including extracting relevant contextual information from previous conversational turns. Due to irrelevant content, error propagation, and redundancy,…

Sound · Computer Science 2024-04-30 Kun Wei , Bei Li , Hang Lv , Quan Lu , Ning Jiang , Lei Xie

Automatic Speech Recognition (ASR) has seen remarkable progress, with models like OpenAI Whisper and NVIDIA Canary achieving state-of-the-art (SOTA) performance in offline transcription. However, these models are not designed for streaming…

Computation and Language · Computer Science 2026-04-07 Tomer Krichli , Bhiksha Raj , Joseph Keshet

Modern systems for automatic speech recognition, including the RNN-Transducer and Attention-based Encoder-Decoder (AED), are designed so that the encoder is not required to alter the time-position of information from the audio sequence into…

Sound · Computer Science 2025-02-11 Adam Stooke , Rohit Prabhavalkar , Khe Chai Sim , Pedro Moreno Mengibar

In this paper, we propose methods for improving the modeling performance of a Transformer-based non-autoregressive text-to-speech (TNA-TTS) model. Although the text encoder and audio decoder handle different types and lengths of data (i.e.,…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-30 Jae-Sung Bae , Tae-Jun Bak , Young-Sun Joo , Hoon-Young Cho

Attention-based encoder-decoder (AED) models have shown impressive performance in ASR. However, most existing AED methods neglect to simultaneously leverage both acoustic and semantic features in decoder, which is crucial for generating…

Computation and Language · Computer Science 2023-05-24 Tian-Hao Zhang , Hai-Bo Qin , Zhi-Hao Lai , Song-Lu Chen , Qi Liu , Feng Chen , Xinyuan Qian , Xu-Cheng Yin

Code-switching speech recognition has attracted an increasing interest recently, but the need for expert linguistic knowledge has always been a big issue. End-to-end automatic speech recognition (ASR) simplifies the building of ASR systems…

Computation and Language · Computer Science 2018-11-02 Ne Luo , Dongwei Jiang , Shuaijiang Zhao , Caixia Gong , Wei Zou , Xiangang Li

Transformer has achieved competitive performance against state-of-the-art end-to-end models in automatic speech recognition (ASR), and requires significantly less training time than RNN-based models. The original Transformer, with…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-14 Wenyong Huang , Wenchao Hu , Yu Ting Yeung , Xiao Chen

In this paper, a multilingual end-to-end framework, called as ATCSpeechNet, is proposed to tackle the issue of translating communication speech into human-readable text in air traffic control (ATC) systems. In the proposed framework, we…

Computation and Language · Computer Science 2021-02-18 Yi Lin , Bo Yang , Linchao Li , Dongyue Guo , Jianwei Zhang , Hu Chen , Yi Zhang

We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC). We improve the core TDS architecture in order to limit the future context and hence…

This paper presents BERT-CTC, a novel formulation of end-to-end speech recognition that adapts BERT for connectionist temporal classification (CTC). Our formulation relaxes the conditional independence assumptions used in conventional CTC…

Audio and Speech Processing · Electrical Eng. & Systems 2023-04-21 Yosuke Higuchi , Brian Yan , Siddhant Arora , Tetsuji Ogawa , Tetsunori Kobayashi , Shinji Watanabe

We introduce CrossNet, a complex spectral mapping approach to speaker separation and enhancement in reverberant and noisy conditions. The proposed architecture comprises an encoder layer, a global multi-head self-attention module, a…

Sound · Computer Science 2024-03-07 Vahid Ahmadi Kalkhorani , DeLiang Wang

Connectionist Temporal Classification (CTC) is a widely used approach for automatic speech recognition (ASR) that performs conditionally independent monotonic alignment. However for translation, CTC exhibits clear limitations due to the…

Computation and Language · Computer Science 2022-10-12 Brian Yan , Siddharth Dalmia , Yosuke Higuchi , Graham Neubig , Florian Metze , Alan W Black , Shinji Watanabe

Estimating time-frequency domain masks for speech enhancement using deep learning approaches has recently become a popular field of research. In this paper, we propose a mask-based speech enhancement framework by using concatenated…

Audio and Speech Processing · Electrical Eng. & Systems 2018-10-29 Ziyi Xu , Maximilian Strake , Tim Fingscheidt

Speech tokenization is the task of representing speech signals as a sequence of discrete units. Such representations can be later used for various downstream tasks including automatic speech recognition, text-to-speech, etc. More relevant…

Sound · Computer Science 2024-06-18 Shoval Messica , Yossi Adi

Radio speech echo is a specific phenomenon in the air traffic control (ATC) domain, which degrades speech quality and further impacts automatic speech recognition (ASR) accuracy. In this work, a time-domain recognition-oriented speech…

Sound · Computer Science 2024-07-31 Xincheng Yu , Dongyue Guo , Jianwei Zhang , Yi Lin

Self-supervised learning has been proved to benefit a wide range of speech processing tasks, such as speech recognition/translation, speaker verification and diarization, etc. However, most of current approaches are computationally…

We propose a novel cascaded cross-modal transformer (CCMT) that combines speech and text transcripts to detect customer requests and complaints in phone conversations. Our approach leverages a multimodal paradigm by transcribing the speech…

Computation and Language · Computer Science 2023-07-31 Nicolae-Catalin Ristea , Radu Tudor Ionescu