Large-Scale Language Model Rescoring on Long-Form Data-Reference-Cited by-同舟云学术

Large-Scale Language Model Rescoring on Long-Form Data

Published:2023-06-04 Issue: Volume: Page:
ISSN:
Container-title:ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
language:
Short-container-title:

Author:

Chen Tongzhou¹,Allauzen Cyril¹,Huang Yinghui¹,Park Daniel¹,Rybach David¹,Huang W. Ronny¹,Cabrera Rodrigo¹,Audhkhasi Kartik¹,Ramabhadran Bhuvana¹,Moreno Pedro J.¹,Riley Michael¹

Affiliation:

1. Google LLC,USA

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10094559/10094560/10096429.pdf?arnumber=10096429

Reference37 articles.

1. Improving Tail Performance of a Deliberation E2E ASR Model Using a Large Text Corpus

2. Scaling laws for neural language models;kaplan,2020

3. End-to-end Speech Recognition With Word-Based Rnn Language Models

4. Less is More: Improved RNN-T Decoding Using Limited Label Context and Path Merging

5. On using monolingual corpora in neural machine translation;gulcehre,2015

Cited by 10 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Ruggedness of Silicon Power MOSFETs–Part II: Device Design Failures and Modeling: A Review;IEEE Transactions on Electron Devices;2024-06

2. Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

3. Correction Focused Language Model Training For Speech Recognition;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

4. SALM: Speech-Augmented Language Model with in-Context Learning for Speech Recognition and Translation;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

5. Train Long and Test Long:Leveraging Full Document Contexts in Speech Processing;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14