English

Towards Maximum Likelihood Training for Transducer-based Streaming Speech Recognition

Audio and Speech Processing 2024-11-27 v1 Machine Learning

Abstract

Transducer neural networks have emerged as the mainstream approach for streaming automatic speech recognition (ASR), offering state-of-the-art performance in balancing accuracy and latency. In the conventional framework, streaming transducer models are trained to maximize the likelihood function based on non-streaming recursion rules. However, this approach leads to a mismatch between training and inference, resulting in the issue of deformed likelihood and consequently suboptimal ASR accuracy. We introduce a mathematical quantification of the gap between the actual likelihood and the deformed likelihood, namely forward variable causal compensation (FoCC). We also present its estimator, FoCCE, as a solution to estimate the exact likelihood. Through experiments on the LibriSpeech dataset, we show that FoCCE training improves the accuracy of the streaming transducers.

Keywords

Cite

@article{arxiv.2411.17537,
  title  = {Towards Maximum Likelihood Training for Transducer-based Streaming Speech Recognition},
  author = {Hyeonseung Lee and Ji Won Yoon and Sungsoo Kim and Nam Soo Kim},
  journal= {arXiv preprint arXiv:2411.17537},
  year   = {2024}
}

Comments

5 pages, 1 figure, 1 table

R2 v1 2026-06-28T20:13:19.143Z