Conference proceeding
Deliberation of Streaming RNN-Transducer by Non-Autoregressive Decoding
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vol.2022-, pp.7452-7456
05/23/2022
DOI: 10.1109/ICASSP43922.2022.9746390
Abstract
We propose to deliberate the hypothesis alignment of a streaming RNN-T model with the previously proposed Align-Refine non-autoregressive decoding method and its improved versions. The method performs a few refinement steps, where each step shares a transformer decoder that attends to both text features (extracted from alignments) and audio features, and outputs complete updated alignments. The transformer decoder is trained with the CTC loss which facilitates parallel greedy decoding, and performs full-context attention to capture label dependencies. We improve Align-Refine by introducing cascaded encoder that captures more audio context before refinement, and alignment augmentation which enforces learning label dependency. We show that, conditioned on hypothesis alignments of a streaming RNN-T model, our method obtains significantly more accurate recognition results than the first-pass RNN-T, with only small amount of model parameters.
Details
- Title: Subtitle
- Deliberation of Streaming RNN-Transducer by Non-Autoregressive Decoding
- Creators
- Weiran Wang - GoogleKe Hu - GoogleTara N. Sainath - Google
- Resource Type
- Conference proceeding
- Publication Details
- ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vol.2022-, pp.7452-7456
- Publisher
- IEEE
- DOI
- 10.1109/ICASSP43922.2022.9746390
- ISSN
- 1520-6149
- eISSN
- 2379-190X
- Language
- English
- Date published
- 05/23/2022
- Academic Unit
- Computer Science
- Record Identifier
- 9984696859102771
Metrics
2 Record Views