DeepAI AI Chat
Log In Sign Up

ASR Error Correction with Constrained Decoding on Operation Prediction

by   Jingyuan Yang, et al.
HUAWEI Technologies Co., Ltd.

Error correction techniques remain effective to refine outputs from automatic speech recognition (ASR) models. Existing end-to-end error correction methods based on an encoder-decoder architecture process all tokens in the decoding phase, creating undesirable latency. In this paper, we propose an ASR error correction method utilizing the predictions of correction operations. More specifically, we construct a predictor between the encoder and the decoder to learn if a token should be kept ("K"), deleted ("D"), or changed ("C") to restrict decoding to only part of the input sequence embeddings (the "C" tokens) for fast inference. Experiments on three public datasets demonstrate the effectiveness of the proposed approach in reducing the latency of the decoding process in ASR correction. It enhances the inference speed by at least three times (3.4 and 5.7 times) while maintaining the same level of accuracy (with WER reductions of 0.53 models compared to a solid encoder-decoder baseline. In the meantime, we produce and release a benchmark dataset contributing to the ASR error correction community to foster research along this line.


page 1

page 2

page 3

page 4


FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition

Error correction techniques have been used to refine the output sentence...

N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Space

Error correction models form an important part of Automatic Speech Recog...

Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding

In this paper, we propose Shallow Aggressive Decoding (SAD) to improve t...

Run-and-back stitch search: novel block synchronous decoding for streaming encoder-decoder ASR

A streaming style inference of encoder-decoder automatic speech recognit...

Parallel Iterative Edit Models for Local Sequence Transduction

We present a Parallel Iterative Edit (PIE) model for the problem of loca...

DiaCorrect: End-to-end error correction for speaker diarization

In recent years, speaker diarization has attracted widespread attention....

Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LM

Connectionist temporal classification (CTC) -based models are attractive...