English
Related papers

Related papers: Stateful Conformer with Cache-based Inference for …

200 papers

Transducer-based models, such as RNN-Transducer and transformer-transducer, have achieved great success in speech recognition. A typical transducer model decodes the output sequence conditioned on the current acoustic state and previously…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-08 Zhengkun Tian , Jiangyan Yi , Ye Bai , Jianhua Tao , Shuai Zhang , Zhengqi Wen

In modern interactive speech-based systems, speech is consumed and transcribed incrementally prior to having disfluencies removed. This post-processing step is crucial for producing clean transcripts and high performance on downstream tasks…

Computation and Language · Computer Science 2022-05-03 Angelica Chen , Vicky Zayats , Daniel D. Walker , Dirk Padfield

With the increased applications of automatic speech recognition (ASR) in recent years, it is essential to automatically insert punctuation marks and remove disfluencies in transcripts, to improve the readability of the transcripts as well…

Computation and Language · Computer Science 2020-03-04 Qian Chen , Mengzhe Chen , Bo Li , Wen Wang

In this paper, we describe the work that we have done to participate in Task1 of the ConferencingSpeech2021 challenge. This task set a goal to develop the solution for multi-channel speech enhancement in a real-time manner. We propose a…

Signal Processing · Electrical Eng. & Systems 2021-04-06 Vasiliy Kuzmin , Fyodor Kravchenko , Artem Sokolov , Jie Geng

Neural transducer-based systems such as RNN Transducers (RNN-T) for automatic speech recognition (ASR) blend the individual components of a traditional hybrid ASR systems (acoustic model, language model, punctuation model, inverse text…

Simultaneous speech-to-text translation is widely useful in many scenarios. The conventional cascaded approach uses a pipeline of streaming ASR followed by simultaneous MT, but suffers from error propagation and extra latency. To alleviate…

Computation and Language · Computer Science 2021-06-15 Junkun Chen , Mingbo Ma , Renjie Zheng , Liang Huang

Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural…

We develop streaming keyword spotting systems using a recurrent neural network transducer (RNN-T) model: an all-neural, end-to-end trained, sequence-to-sequence model which jointly learns acoustic and language model components. Our models…

Computation and Language · Computer Science 2017-10-27 Yanzhang He , Rohit Prabhavalkar , Kanishka Rao , Wei Li , Anton Bakhtin , Ian McGraw

Conventional Deep Learning frameworks for continuous sign language recognition (CSLR) are comprised of a single or multi-modal feature extractor, a sequence-learning module, and a decoder for outputting the glosses. The sequence learning…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Neena Aloysius , Geetha M , Prema Nedungadi

This paper tackles several challenges that arise when integrating Automatic Speech Recognition (ASR) and Machine Translation (MT) for real-time, on-device streaming speech translation. Although state-of-the-art ASR systems based on…

Computation and Language · Computer Science 2025-08-20 Zeeshan Ahmed , Frank Seide , Niko Moritz , Ju Lin , Ruiming Xie , Simone Merello , Zhe Liu , Christian Fuegen

Automatic speech recognition research focuses on training and evaluating on static datasets. Yet, as speech models are increasingly deployed on personal devices, such models encounter user-specific distributional shifts. To simulate this…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-26 Anuj Diwan , Ching-Feng Yeh , Wei-Ning Hsu , Paden Tomasello , Eunsol Choi , David Harwath , Abdelrahman Mohamed

This work introduces TTS-Transducer - a novel architecture for text-to-speech, leveraging the strengths of audio codec models and neural transducers. Transducers, renowned for their superior quality and robustness in speech recognition, are…

Audio and Speech Processing · Electrical Eng. & Systems 2025-04-16 Vladimir Bataev , Subhankar Ghosh , Vitaly Lavrukhin , Jason Li

In streaming automatic speech recognition (ASR), it is desirable to reduce latency as much as possible while having minimum impact on recognition accuracy. Although a few existing methods are able to achieve this goal, they are difficult to…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-02 Wei Kang , Zengwei Yao , Fangjun Kuang , Liyong Guo , Xiaoyu Yang , Long lin , Piotr Żelasko , Daniel Povey

End-to-end (E2E) automatic speech recognition (ASR) models, by now, have shown competitive performance on several benchmarks. These models are structured to either operate in streaming or non-streaming mode. This work presents cascaded…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-29 Arun Narayanan , Tara N. Sainath , Ruoming Pang , Jiahui Yu , Chung-Cheng Chiu , Rohit Prabhavalkar , Ehsan Variani , Trevor Strohman

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

This paper introduces a novel training framework called Focused Discriminative Training (FDT) to further improve streaming word-piece end-to-end (E2E) automatic speech recognition (ASR) models trained using either CTC or an interpolation of…

Machine Learning · Computer Science 2024-08-26 Adnan Haider , Xingyu Na , Erik McDermott , Tim Ng , Zhen Huang , Xiaodan Zhuang

In this work, we propose novel decoding algorithms to enable streaming automatic speech recognition (ASR) on unsegmented long-form recordings without voice activity detection (VAD), based on monotonic chunkwise attention (MoChA) with an…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-16 Hirofumi Inaguma , Tatsuya Kawahara

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 introduce a novel neural network module that adeptly handles recursive data flow in neural network architectures. At its core, this module employs a self-consistent approach where a set of recursive equations is solved iteratively,…

Computation and Language · Computer Science 2024-10-07 Konstantin Kolokolov , Pavel Pekichev , Karthik Raghunathan

Transformer-based models have dramatically increased their size and parameter count to tackle increasingly complex tasks. At the same time, there is a growing demand for high performance, low-latency inference on devices with limited…

Machine Learning · Computer Science 2026-04-01 Ginés Carreto Picón , Peng Yuan Zhou , Qi Zhang , Alexandros Iosifidis