Better Intermediates Improve CTC Inference
Tatsuya Komatsu, Yusuke Fujita, Jaesong Lee, Lukas Jyuhn‐Hsiarn Lee, Shinji Watanabe, Yusuke Kida · Interspeech 2022 · 2022
This paper proposes a method for improved CTC inference with searched intermediates and multi-pass conditioning.The paper first formulates self-conditioned CTC as a probabilistic model with an intermediate prediction as a latent representation and provides a tractable conditioning framework.We then propose two new conditioning methods based on the new formulation:(1) Searched intermediate conditioning that refines intermediate predictions with beam-search, (2) Multi-pass conditioning that uses predictions of previous inference for conditioning the next inference.These new approaches enable better conditioning than the original self-conditioned CTC during inference and improve the final performance.Experiments with the LibriSpeech dataset show relative 3%/12% performance improvement at the maximum in test clean/other sets compared to the original selfconditioned CTC.