Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition

Jinming Chen, Jingyi Fang, Yuanzhong Zheng, Yaoxuan Wang, Haojun Fei
7/3/2024
cs.SDcs.AIeess.AS

No confident code implementation found for this paper. 4 possible matches can be shown below.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 4 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Accented Speech Recognition With Accent-specific Codebooks

81% match1 repo192023

Streaming Non-Autoregressive Model for Accent Conversion and Pronunciation Improvement

80% match2025

Unifying Streaming and Non-streaming Zipformer-based ASR

79% match2025

Convert and Speak: Zero-shot Accent Conversion with Minimum Supervision

79% match2024

Acoustic Model Fusion for End-to-end Speech Recognition

78% match2023

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition

77% match2025

Cite this paper

@article{chen2024qifusionnet,
  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},
  year   = {2024},
  eprint = {2407.03026},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2407.03026v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2407.03026.svg)](https://codeofpaper.com/paper/2407.03026)

Discussion