NAACL 2024long2 citations

Massive End-to-end Speech Recognition Models with Time Reduction

Weiran Wang, Rohit Prabhavalkar, Haozhe Shan, Zhong Meng, Dongseong Hwang, Qiujia Li, Khe Chai Sim, Bo Li

Abstract

We investigate massive end-to-end automatic speech recognition (ASR) models with efficiency improvements achieved by time reduction. The encoders of our models use the neural architecture of Google’s universal speech model (USM), with additional funnel pooling layers to significantly reduce the frame rate and speed up training and inference. We also explore a few practical methods to mitigate potential accuracy loss due to time reduction, while enjoying most efficiency gain. Our methods are demonstrated to work with both Connectionist Temporal Classification (CTC) and RNN-Transducer (RNN-T), with up to 2B model parameters, and over two domains. For a large-scale voice search recognition task, we perform extensive studies on vocabulary size, time reduction strategy, and its generalization performance on long-form test sets, and show that a 900M RNN-T is very tolerant to severe time reduction, with as low encoder output frame rate as 640ms. We also provide ablation studies on the Librispeech benchmark for important training hyperparameters and architecture designs, in training 600M RNN-T models at the frame rate of 160ms.

BibTeX
@inproceedings{wang-etal-2024-massive,
    title = "Massive End-to-end Speech Recognition Models with Time Reduction",
    author = "Wang, Weiran  and
      Prabhavalkar, Rohit  and
      Shan, Haozhe  and
      Meng, Zhong  and
      Hwang, Dongseong  and
      Li, Qiujia  and
      Sim, Khe Chai  and
      Li, Bo  and
      Qin, James  and
      Cai, Xingyu  and
      Stooke, Adam  and
      Zheng, Chengjian  and
      He, Yanzhang  and
      Sainath, Tara  and
      Moreno Mengibar, Pedro",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.naacl-long.344/",
    doi = "10.18653/v1/2024.naacl-long.344",
    pages = "6206--6217"
}
Massive End-to-end Speech Recognition Models with Time Reduction · NAACL 2024