Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition
Abstract
Currently, end-to-end (E2E) speech recognition methods have achieved promising performance. However, auto speech recognition (ASR) models still face challenges in recognizing multi-accent speech accurately. We propose a layer-adapted fusion (LAF) model, called Qifusion-Net, which does not require any prior knowledge about the target accent. Based on dynamic chunk strategy, our approach enables streaming decoding and can extract frame-level acoustic feature, facilitating fine-grained information fusion. Experiment results demonstrate that our proposed methods outperform the baseline with relative reductions of 22.1 and 17.2 in character error rate (CER) across multi accent test datasets on KeSpeech and MagicData-RMAC.
Cite
@article{arxiv.2407.03026,
title = {Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition},
author = {Jinming Chen and Jingyi Fang and Yuanzhong Zheng and Yaoxuan Wang and Haojun Fei},
journal= {arXiv preprint arXiv:2407.03026},
year = {2024}
}
Comments
accpeted by interspeech 2014, 5 pages, 1 figure