English

Multi-mode Transformer Transducer with Stochastic Future Context

Audio and Speech Processing 2021-06-21 v1 Computation and Language Sound

Abstract

Automatic speech recognition (ASR) models make fewer errors when more surrounding speech information is presented as context. Unfortunately, acquiring a larger future context leads to higher latency. There exists an inevitable trade-off between speed and accuracy. Naively, to fit different latency requirements, people have to store multiple models and pick the best one under the constraints. Instead, a more desirable approach is to have a single model that can dynamically adjust its latency based on different constraints, which we refer to as Multi-mode ASR. A Multi-mode ASR model can fulfill various latency requirements during inference -- when a larger latency becomes acceptable, the model can process longer future context to achieve higher accuracy and when a latency budget is not flexible, the model can be less dependent on future context but still achieve reliable accuracy. In pursuit of Multi-mode ASR, we propose Stochastic Future Context, a simple training procedure that samples one streaming configuration in each iteration. Through extensive experiments on AISHELL-1 and LibriSpeech datasets, we show that a Multi-mode ASR model rivals, if not surpasses, a set of competitive streaming baselines trained with different latency budgets.

Keywords

Cite

@article{arxiv.2106.09760,
  title  = {Multi-mode Transformer Transducer with Stochastic Future Context},
  author = {Kwangyoun Kim and Felix Wu and Prashant Sridhar and Kyu J. Han and Shinji Watanabe},
  journal= {arXiv preprint arXiv:2106.09760},
  year   = {2021}
}

Comments

Accepted to Interspeech 2021

R2 v1 2026-06-24T03:20:02.396Z