mlsanityData to 7 Oct 2026

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

arXiv 2407.03026 ↗First posted 3 Jul 2024cs.SD cs.AI eess.AScited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 21 of its 29 references that are in the map. First posted on arXiv 3 Jul 2024.

Builds on

21 of 29 references.

References · 21

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  2. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  3. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  4. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  5. 2022Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognitioncited by 139
  6. 2023FunASR: A Fundamental End-to-End Speech Recognition Toolkitcited by 92
  7. 2020ESPnet-ST: All-in-One Speech Translation Toolkitcited by 82
  8. 2022WeNet 2.0: More Productive End-to-End Speech Recognition Toolkitcited by 46
  9. 2021Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognitioncited by 42
  10. 2018Domain Adversarial Training for Accented Speech Recognitioncited by 40
  11. 2021An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognitioncited by 39
  12. 2022Open Source MagicData-RAMC: A Rich Annotated Mandarin Conversational(RAMC) Speech Datasetcited by 36
9 more
  1. 2020REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabelingcited by 18
  2. 2021Best of Both Worlds: Robust Accented Speech Recognition with Adversarial Transfer Learningcited by 17
  3. 2022Layer-wise Fast Adaptation for End-to-End Multi-Accent Speech Recognitioncited by 12
  4. 2023Improving Accented Speech Recognition with Multi-Domain Trainingcited by 5
  5. 2023Conversational Speech Recognition by Learning Audio-textual Cross-modal Contextual Representationcited by 4
  6. 2023Multi-pass Training and Cross-information Fusion for Low-resource End-to-end Accented Speech Recognitioncited by 3
  7. 2023Decoupling and Interacting Multi-Task Learning Network for Joint Speech and Accent Recognitioncited by 3
  8. 2020A New Approach to Accent Recognition and Conversion for Mandarin Chinesecited by 2
  9. 2023Advanced accent/dialect identification and accentedness assessment with multi-embedding models and automatic speech recognitioncited by 1

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Accent-Invariant Automatic Speech Recognition via Saliency-Driven Spectrogram Maskingcited by 2
  2. 2025Multi-Accent Mandarin Dry-Vocal Singing Dataset: Benchmark for Singing Accent Recognitioncited by 1