Streaming Speech Recognition

Streaming Speech Recognition is a type of automatic speech recognition that processes audio input in real time as a continuous data stream, distinguishing itself from batch or offline methods by enabling incremental transcription with minimal latency.

181

Publications

Citations

556

Authors

Institutions

Publications per year

2017–2026

124

Variants

Real-time Speech Recognition

Parents

Speech Recognition

Publications

181

Streaming End-to-end Speech Recognition for Mobile Devices

Yanzhang He, Tara N. Sainath, Rohit Prabhavalkar et al. · 2019 · 606 citations

Computing, Computer Science, Machine Learning +13

Audio-visual speech modeling for continuous speech recognition

Stéphane Dupont, Juergen Luettin · IEEE Transactions on Multimedia · 2000 · 601 citations · Full text

Computing, Computer Science, Computer Vision +16

Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss

Qian Zhang, Lu Han, Haşim Sak et al. · 2020 · 454 citations

Computing, Computer Science, Machine Learning +12

Exploring architectures, data and units for streaming end-to-end speech recognition with RNN-transducer

Kanishka Rao, Haşim Sak, Rohit Prabhavalkar · 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) · 2017 · 371 citations

Computing, Computer Science, Machine Learning +14

Transformer-Based Acoustic Modeling for Hybrid Speech Recognition

Yongqiang Wang, Abdelrahman Mohamed, Chunxi Liu et al. · 2020 · 257 citations · Full text

Computing, Linguistics, Acoustics +14

1–5 of 181

Authors

556

TN
Tara N. Sainath
Google (United States), United States
21 publications · 1.8K citations
17
h-index
JL
Jinyu Li
Microsoft (United States), United States
17 publications · 865 citations
16
h-index
RP
Ruoming Pang
Google (United States), United States
14 publications · 1.2K citations
13
h-index
CC
Chung‐Cheng Chiu
Google (United States), United States
14 publications · 665 citations
13
h-index
YW
Yonghui Wu
Google (United States), United States
15 publications · 1.5K citations
13
h-index

1–5 of 556

Institutions

1–8 of 95

Venues

arXiv (Cornell University)
Repository · 22 publications · 477 citations
14
h-index
Interspeech 2022
Conference · 10 publications · 300 citations
9
h-index
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Conference · 8 publications · 170 citations
8
h-index
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
4 publications · 316 citations
4
h-index
IEEE International Conference on Acoustics Speech and Signal Processing
Conference · 4 publications · 100 citations
4
h-index

1–5