English
Related papers

Related papers: A comparison of streaming models and data augmenta…

200 papers

We investigate a monotonic multihead attention (MMA) by extending hard monotonic attention to Transformer-based automatic speech recognition (ASR) for online streaming applications. For streaming inference, all monotonic attention (MA)…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-01 Hirofumi Inaguma , Masato Mimura , Tatsuya Kawahara

Having a sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-to-sequence model, but has shown a significant degradation in…

Computation and Language · Computer Science 2017-12-06 Tara N. Sainath , Chung-Cheng Chiu , Rohit Prabhavalkar , Anjuli Kannan , Yonghui Wu , Patrick Nguyen , Zhifeng Chen

The Dual-Path Convolution Recurrent Network (DPCRN) was proposed to effectively exploit time-frequency domain information. By combining the DPRNN module with Convolution Recurrent Network (CRN), the DPCRN obtained a promising performance in…

Sound · Computer Science 2023-06-16 Liang Wan , Hongqing Liu , Yi Zhou , Jie Ji

Applying large pre-trained speech models like Whisper has shown promise in reducing training costs for various speech tasks. However, integrating these models into streaming systems remains a challenge. This paper presents a novel…

Computation and Language · Computer Science 2025-06-05 Yinfeng Xia , Huiyan Li , Chenyang Le , Manhong Wang , Yutao Sun , Xingyang Ma , Yanmin Qian

In this paper, we propose an online attention mechanism, known as cumulative attention (CA), for streaming Transformer-based automatic speech recognition (ASR). Inspired by monotonic chunkwise attention (MoChA) and head-synchronous…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-14 Mohan Li , Shucong Zhang , Catalin Zorila , Rama Doddipatla

Mispronunciation detection and diagnosis (MDD) is a popular research focus in computer-aided pronunciation training (CAPT) systems. End-to-end (e2e) approaches are becoming dominant in MDD. However an e2e MDD model usually requires entire…

Computation and Language · Computer Science 2022-06-30 Nianzu Zheng , Liqun Deng , Wenyong Huang , Yu Ting Yeung , Baohua Xu , Yuanyuan Guo , Yasheng Wang , Xiao Chen , Xin Jiang , Qun Liu

Streaming processing of speech audio is required for many contemporary practical speech recognition tasks. Even with the large corpora of manually transcribed speech data available today, it is impossible for such corpora to cover…

Computation and Language · Computer Science 2021-04-12 Rodrigo Cabrera , Xiaofeng Liu , Mohammadreza Ghodsi , Zebulun Matteson , Eugene Weinstein , Anjuli Kannan

Recurrent neural network transducers (RNN-T) have been successfully applied in end-to-end speech recognition. However, the recurrent structure makes it difficult for parallelization . In this paper, we propose a self-attention transducer…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-25 Zhengkun Tian , Jiangyan Yi , Jianhua Tao , Ye Bai , Zhengqi Wen

Unification of automatic speech recognition (ASR) systems reduces development and maintenance costs, but training a single model to perform well in both offline and low-latency streaming settings remains challenging. We present a Unified…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-22 Andrei Andrusenko , Vladimir Bataev , Lilit Grigoryan , Nune Tadevosyan , Vitaly Lavrukhin , Boris Ginsburg

RNN-Transducers (RNN-Ts) have gained widespread acceptance as an end-to-end model for speech to text conversion because of their high accuracy and streaming capabilities. A typical RNN-T independently encodes the input audio and the text…

Computation and Language · Computer Science 2023-07-12 Vinit S. Unni , Ashish Mittal , Preethi Jyothi , Sunita Sarawagi

Recent studies reveal the potential of recurrent neural network transducer (RNN-T) for end-to-end (E2E) speech recognition. Among some most popular E2E systems including RNN-T, Attention Encoder-Decoder (AED), and Connectionist Temporal…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-19 Bin Wang , Yan Yin , Hui Lin

Large Language Model (LLM) based text-to-speech (TTS) systems have demonstrated remarkable capabilities in handling large speech datasets and generating natural speech for new speakers. However, LLM-based TTS models are not robust as the…

Data augmentation has proven to be a promising prospect in improving the performance of deep learning models by adding variability to training data. In previous work with developing a noise robust acoustic-to-articulatory speech inversion…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-02 Yashish M. Siriwardena , Ahmed Adel Attia , Ganesh Sivaraman , Carol Espy-Wilson

End-to-end multi-talker speech recognition is an emerging research trend in the speech community due to its vast potential in applications such as conversation and meeting transcriptions. To the best of our knowledge, all existing research…

Sound · Computer Science 2021-05-12 Liang Lu , Naoyuki Kanda , Jinyu Li , Yifan Gong

Deep learning has achieved substantial improvement on single-channel speech enhancement tasks. However, the performance of multi-layer perceptions (MLPs)-based methods is limited by the ability to capture the long-term effective history…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-19 Qiquan Zhang , Aaron Nicolson , Mingjiang Wang , Kuldip K. Paliwal , Chenxu Wang

Neural Machine Translation (NMT) models have been proved strong when translating clean texts, but they are very sensitive to noise in the input. Improving NMT models robustness can be seen as a form of "domain" adaption to noise. The…

Computation and Language · Computer Science 2019-11-12 Zhenhao Li , Lucia Specia

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. To improve robustness of speaker recognition system performance in…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-19 Yanpei Shi , Qiang Huang , Thomas Hain

Attention-based end-to-end models such as Listen, Attend and Spell (LAS), simplify the whole pipeline of traditional automatic speech recognition (ASR) systems and become popular in the field of speech recognition. In previous work,…

Computation and Language · Computer Science 2019-04-26 Ruchao Fan , Pan Zhou , Wei Chen , Jia Jia , Gang Liu

Because of its streaming nature, recurrent neural network transducer (RNN-T) is a very promising end-to-end (E2E) model that may replace the popular hybrid model for automatic speech recognition. In this paper, we describe our recent…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-31 Jinyu Li , Rui Zhao , Zhong Meng , Yanqing Liu , Wenning Wei , Sarangarajan Parthasarathy , Vadim Mazalov , Zhenghao Wang , Lei He , Sheng Zhao , Yifan Gong

The RNN-Transducers and improved attention-based encoder-decoder models are widely applied to streaming speech recognition. Compared with these two end-to-end models, the CTC model is more efficient in training and inference. However, it…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-06 Zhengkun Tian , Jiangyan Yi , Ye Bai , Jianhua Tao , Shuai Zhang , Zhengqi Wen