Tied & Reduced RNN-T Decoder

15 September 2021

Papers citing "Tied & Reduced RNN-T Decoder"

39 / 39 papers shown

Title
Text Injection for Neural Contextual Biasing Zhong Meng Zelin Wu Rohit Prabhavalkar Cal Peyser Weiran Wang Nanxin Chen Tara N. Sainath Bhuvana Ramabhadran 18 3 0 05 Jun 2024
Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASR Zelin Wu Gan Song Christopher Li Pat Rondon Zhong Meng ... D. Caseiro Golan Pundak Tsendsuren Munkhdalai Angad Chandorkar Rohit Prabhavalkar 18 3 0 15 Apr 2024
Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models Rohit Prabhavalkar Zhong Meng Weiran Wang Adam Stooke Xingyu Cai Yanzhang He Arun Narayanan Dongseong Hwang Tara N. Sainath Pedro J. Moreno 25 8 0 27 Feb 2024
Improved Long-Form Speech Recognition by Jointly Modeling the Primary and Non-primary Speakers Guru Prakash Arumugam Shuo-yiin Chang Tara N. Sainath Rohit Prabhavalkar Quan Wang Shaan Bijwadia 14 3 0 18 Dec 2023
On the compression of shallow non-causal ASR models using knowledge distillation and tied-and-reduced decoder for low-latency on-device speech recognition Nagaraj Adiga Jinhwan Park Chintigari Shiva Kumar Shatrughan Singh Kyungmin Lee Chanwoo Kim Dhananjaya N. Gowda 11 1 0 15 Dec 2023
Partial Rewriting for Multi-Stage ASR A. Bruguier David Qiu Yanzhang He 14 0 0 08 Dec 2023
Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithm Weiran Wang Zelin Wu D. Caseiro Tsendsuren Munkhdalai K. Sim ... Rohit Prabhavalkar Zhong Meng Ding Zhao Tara N. Sainath P. M. Mengibar 48 5 0 29 Sep 2023
Massive End-to-end Models for Short Search Queries Weiran Wang Rohit Prabhavalkar Dongseong Hwang Qiujia Li K. Sim ... Zhong Meng CJ Zheng Yanzhang He Tara N. Sainath P. M. Mengibar 22 2 0 22 Sep 2023
Towards Word-Level End-to-End Neural Speaker Diarization with Auxiliary Network Yiling Huang Weiran Wang Guanlong Zhao Hank Liao Wei Xia Quan Wang 17 4 0 15 Sep 2023
CIF-T: A Novel CIF-based Transducer Architecture for Automatic Speech Recognition Tian-Hao Zhang Dinghao Zhou Guiping Zhong Jiaming Zhou Baoxiang Li 10 3 0 26 Jul 2023
Large-scale Language Model Rescoring on Long-form Data Tongzhou Chen Cyril Allauzen Yinghui Huang Daniel S. Park David Rybach ... Rodrigo Cabrera Kartik Audhkhasi Bhuvana Ramabhadran Pedro J. Moreno Michael Riley 22 14 0 13 Jun 2023
Modular Domain Adaptation for Conformer-Based Streaming ASR Qiujia Li Bo-wen Li DongSeon Hwang Tara N. Sainath P. M. Mengibar 23 12 0 22 May 2023
Lego-Features: Exporting modular encoder features for streaming and deliberation ASR Rami Botros Rohit Prabhavalkar J. Schalkwyk Ciprian Chelba Tara N. Sainath Franccoise Beaufays AuLLM 13 2 0 31 Mar 2023
Practical Conformer: Optimizing size, speed and flops of Conformer for on-Device and cloud ASR Rami Botros Anmol Gulati Tara N. Sainath K. Choromanski Ruoming Pang Trevor Strohman Weiran Wang Jiahui Yu MQ 10 3 0 31 Mar 2023
End-to-End Speech Recognition: A Survey Rohit Prabhavalkar Takaaki Hori Tara N. Sainath Ralf Schluter Shinji Watanabe VLM 21 148 0 03 Mar 2023
JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition Zhong Meng Weiran Wang Rohit Prabhavalkar Tara N. Sainath Tongzhou Chen Ehsan Variani Yu Zhang Bo-wen Li Andrew Rosenberg Bhuvana Ramabhadran AuLLM VLM 15 11 0 16 Feb 2023
Dual Learning for Large Vocabulary On-Device ASR Cal Peyser Ronny Huang Tara N. Sainath Rohit Prabhavalkar M. Picheny K. Cho SSL 11 1 0 11 Jan 2023
LongFNT: Long-form Speech Recognition with Factorized Neural Transducer Xun Gong Yu-Huan Wu Jinyu Li Shujie Liu Rui Zhao Xie Chen Y. Qian RALM 11 10 0 17 Nov 2022
Factorized Blank Thresholding for Improved Runtime Efficiency of Neural Transducers Duc Le Frank Seide Yuhao Wang Y. Li Kjell Schubert Ozlem Kalinli M. Seltzer 11 6 0 02 Nov 2022
Modular Hybrid Autoregressive Transducer Zhong Meng Tongzhou Chen Rohit Prabhavalkar Yu Zhang Gary Wang ... Bhuvana Ramabhadran W. R. Huang Ehsan Variani Yinghui Huang Pedro J. Moreno 21 20 0 31 Oct 2022
JOIST: A Joint Speech and Text Streaming Model For ASR Tara N. Sainath Rohit Prabhavalkar Ankur Bapna Yu Zhang Zhouyuan Huo Zhehuai Chen Bo-wen Li Weiran Wang Trevor Strohman RALM AuLLM 38 35 0 13 Oct 2022
Multi-stage Progressive Compression of Conformer Transducer for On-device Speech Recognition Jash Rathod Nauman Dawalatabad Shatrughan Singh Dhananjaya N. Gowda 12 9 0 01 Oct 2022
A Language Agnostic Multilingual Streaming On-Device ASR System Bo-wen Li Tara N. Sainath Ruoming Pang Shuo-yiin Chang Qiumin Xu ... Qiao Liang Heguang Liu Yanzhang He Parisa Haghani Sameer Bidichandani AuLLM 19 11 0 29 Aug 2022
Streaming Intended Query Detection using E2E Modeling for Continued Conversation Shuo-yiin Chang Guru Prakash Zelin Wu Qiao Liang Tara N. Sainath Bo-wen Li Adam Stambler Shyam Upadhyay Manaal Faruqui Trevor Strohman 27 5 0 29 Aug 2022
Turn-Taking Prediction for Natural Conversational Speech Shuo-yiin Chang Bo-wen Li Tara N. Sainath Chaoyang Zhang Trevor Strohman Qiao Liang Yanzhang He 35 17 0 29 Aug 2022
VQ-T: RNN Transducers using Vector-Quantized Prediction Network States Jiatong Shi G. Saon David Haws Shinji Watanabe Brian Kingsbury 9 3 0 03 Aug 2022
Improving Deliberation by Text-Only and Semi-Supervised Training Ke Hu Tara N. Sainath Yanzhang He Rohit Prabhavalkar Trevor Strohman S. Mavandadi Weiran Wang 19 12 0 29 Jun 2022
On the Prediction Network Architecture in RNN-T for ASR Dario Albesano Jesús Andrés-Ferrer Nicola Ferri Puming Zhan AI4TS 11 0 0 29 Jun 2022
Pruned RNN-T for fast, memory-efficient ASR training Fangjun Kuang Liyong Guo Wei Kang Long Lin Mingshuang Luo Zengwei Yao Daniel Povey 9 63 0 23 Jun 2022
E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR W. R. Huang Shuo-yiin Chang David Rybach Rohit Prabhavalkar Tara N. Sainath Cyril Allauzen Cal Peyser Zhiyun Lu VLM 18 23 0 22 Apr 2022
Detecting Unintended Memorization in Language-Model-Fused ASR W. R. Huang Steve Chien Om Thakkar Rajiv Mathews 20 11 0 20 Apr 2022
Improving Rare Word Recognition with LM-aware MWER Training Weiran Wang Tongzhou Chen Tara N. Sainath Ehsan Variani Rohit Prabhavalkar ... S. Mavandadi Cal Peyser Trevor Strohman Yanzhang He David Rybach KELM 22 13 0 15 Apr 2022
A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes Shaojin Ding Weiran Wang Ding Zhao Tara N. Sainath Yanzhang He ... Qiao Liang Dongseong Hwang Ian McGraw Rohit Prabhavalkar Trevor Strohman 12 17 0 13 Apr 2022
4-bit Conformer with Native Quantization Aware Training for Speech Recognition Shaojin Ding Phoenix Meadowlark Yanzhang He Lukasz Lew Shivani Agrawal Oleg Rybakov MQ 24 32 0 29 Mar 2022
Deliberation of Streaming RNN-Transducer by Non-autoregressive Decoding Weiran Wang Ke Hu Tara N. Sainath 14 21 0 01 Dec 2021
Recent Advances in End-to-End Automatic Speech Recognition Jinyu Li VLM 13 362 0 02 Nov 2021
Echo State Speech Recognition H. Shrivastava Ankush Garg Yuan Cao Yu Zhang Tara N. Sainath 37 22 0 18 Feb 2021
Less Is More: Improved RNN-T Decoding Using Limited Label Context and Path Merging Rohit Prabhavalkar Yanzhang He David Rybach S. Campbell A. Narayanan Trevor Strohman Tara N. Sainath 41 35 0 12 Dec 2020
Minimum Bayes Risk Training of RNN-Transducer for End-to-End Speech Recognition Chao Weng Chengzhu Yu Jia Cui Chunlei Zhang Dong Yu 69 39 0 28 Nov 2019