Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment

2020/10/24 by Ethan A. Chi, Julian Salazar, Chi, Ethan A. +3 · 3 citations
Computer Science · #Speech Recognition and Synthesis #Music and Audio Processing #Speech and Audio Processing

paper · pdf · doi:10.48550/arxiv.2010.14233

Abstract

Non-autoregressive models greatly improve decoding speed over typical sequence-to-sequence models, but suffer from degraded performance. Infilling and iterative refinement models make up some of this gap by editing the outputs of a non-autoregressive model, but are constrained in the edits that they can make. We propose iterative realignment, where refinements occur over latent alignments rather than output sequence space. We demonstrate this in speech recognition with Align-Refine, an end-to-end Transformer-based model which refines connectionist temporal classification (CTC) alignments to allow length-changing insertions and deletions. Align-Refine outperforms Imputer and Mask-CTC, matching an autoregressive baseline on WSJ at 1/14th the real-time factor and attaining a LibriSpeech test-other WER of 9.0% without an LM. Our model is strong even in one iteration with a shallower decoder.

Cited by

• Towards Effective and Efficient Non-autoregressive decoders for Conformer and LLM-based ASR using Block-based Attention Mask
• Audio-Conditioned Diffusion LLMs for ASR and Deliberation Processing
• A Survey on Non-Intrusive ASR Refinement: From Output-Level Correction to Full-Model Distillation

Related

• Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework
• Less Peaky and More Accurate CTC Forced Alignment by Label Priors
• Streaming Align-Refine for Non-autoregressive Deliberation
• Iterative pseudo-forced alignment by acoustic CTC loss for self-supervised ASR domain adaptation
• Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation