Paraformer: Fast And Accurate Parallel Transformer For Non-autoregressive End-to-end Speech Recognition
2022 · Zhifu Gao, Shiliang Zhang, Ian McLoughlin, et al.
Abstract
Transformers have recently dominated the ASR field. Although able to yield good performance, they involve an autoregressive (AR) decoder to generate tokens one by one, which is computationally inefficient. To speed up inference, non-autoregressive (NAR) methods, e.g. single-step NAR, were designed, to enable parallel generation. However, due to an independence assumption within the output tokens, performance of single-step NAR is inferior to that of AR models, especially with a large-scale corpus. There are two challenges to improving single-step NAR: Firstly to accurately predict the number of output tokens and extract hidden variables; secondly, to enhance modeling of interdependence between output tokens. To tackle both challenges, we propose a fast and accurate parallel transformer, termed Paraformer. This utilizes a continuous integrate-and-fire based predictor to predict the number of tokens and generate hidden variables. A glancing language model (GLM) sampler then generates sem
Authors
(none)
Tags
Stats
Related papers
- Paraformer-v2: An Improved Non-autoregressive Transformer For Noise-robust Speech Recognition (2024)0.00
- TSNAT: Two-step Non-autoregressvie Transformer Models For Speech Recognition (2021)10.61
- Fast Offline Transformer-based End-to-end Automatic Speech Recognition For Real-world Applications (2021)7.16
- Non-autoregressive Transformer With Unified Bidirectional Decoder For Automatic Speech Recognition (2021)7.81
- Improving Non-autoregressive End-to-end Speech Recognition With Pre-trained Acoustic And Language Models (2022)10.07
- Synchronous Transformers For End-to-end Speech Recognition (2019)12.02
- Non-autoregressive Transformer ASR With Ctc-enhanced Decoder Input (2020)10.97
- Non-autoregressive End-to-end Approaches For Joint Automatic Speech Recognition And Spoken Language Understanding (2023)5.84