Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment
This addresses the speed-accuracy trade-off in speech recognition for real-time applications, representing a novel method rather than an incremental improvement.
The paper tackled the performance degradation in non-autoregressive speech recognition by proposing iterative realignment over latent alignments, resulting in matching an autoregressive baseline on WSJ at 1/14th the real-time factor and achieving a LibriSpeech test-other WER of 9.0% without a language model.
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.