1 citations · 1 across the 7 of their papers we have counts for
7 papers
Data Quality Issues in Multilingual Speech Datasets: The Need for Sociolinguistic Awareness and Proactive Language Planning
Mingfei Lau, Qian Chen, Yeming Fang +3
Our quality audit for three widely used public multilingual speech datasets - Mozilla Common Voice 17.0, FLEURS, and Vox Populi - shows that in some languages, these datasets suffe…
LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriors
Rao Ma, Tongzhou Chen, Kartik Audhkhasi +1
Recently, large-scale pre-trained speech encoders and Large Language Models (LLMs) have been released, which show state-of-the-art performance on a range of spoken language process…
Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study
W. Ronny Huang, Cyril Allauzen, Tongzhou Chen +7
In the era of large models, the autoregressive nature of decoding often results in latency serving as a significant bottleneck. We propose a non-autoregressive LM-fused ASR system…
Large-scale Language Model Rescoring on Long-form Data
Tongzhou Chen, Cyril Allauzen, Yinghui Huang +8
In this work, we study the impact of Large-scale Language Models (LLM) on Automated Speech Recognition (ASR) of YouTube videos, which we use as a source for long-form ASR. We demon…
JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition
Zhong Meng, Weiran Wang, Rohit Prabhavalkar +7
We propose JEIT, a joint end-to-end (E2E) model and internal language model (ILM) training method to inject large-scale unpaired text into ILM during E2E training which improves ra…
Modular Hybrid Autoregressive Transducer
Zhong Meng, Tongzhou Chen, Rohit Prabhavalkar +10
Text-only adaptation of a transducer model remains challenging for end-to-end speech recognition since the transducer has no clearly separated acoustic model (AM), language model (…
Improving Rare Word Recognition with LM-aware MWER Training
Weiran Wang, Tongzhou Chen, Tara N. Sainath +10
Language models (LMs) significantly improve the recognition accuracy of end-to-end (E2E) models on words rarely seen during training, when used in either the shallow fusion or the…