mlsanityData to 14 Oct 2026

Multi-pass Training and Cross-information Fusion for Low-resource End-to-end Accented Speech Recognition

arXiv 2306.11309 ↗First posted 20 Jun 2023cs.SD cs.CL eess.AScited by 3

Not on the map. Why?

Abstract (arXiv)

Low-resource accented speech recognition is one of the important challenges faced by current ASR technology in practical applications. In this study, we propose a Conformer-based architecture, called Aformer, to leverage both the acoustic information from large non-accented and limited accented training data. Specifically, a general encoder and an accent encoder are designed in the Aformer to extract complementary acoustic information. Moreover, we propose to train the Aformer in a multi-pass manner, and investigate three cross-information fusion methods to effectively combine the information from both general and accent encoders. All experiments are conducted on both the accented English and Mandarin ASR tasks. Results show that our proposed methods outperform the strong Conformer baseline by relative 10.2% to 24.5% word/character error rate reduction on six in-domain and out-of-domain accented test sets.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 24 of its 33 references that are in the map. First posted on arXiv 20 Jun 2023.

Builds on

24 of 33 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  4. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  5. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  6. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  7. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  8. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  9. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 558
  10. 2015Listen, Attend and Spellcited by 543
  11. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 373
  12. 2017State-of-the-art Speech Recognition With Sequence-to-Sequence Modelscited by 196
12 more
  1. 2020Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognitioncited by 187
  2. 2015End-to-End Attention-based Large Vocabulary Speech Recognitioncited by 151
  3. 2020Recent Developments on ESPnet Toolkit Boosted by Conformercited by 132
  4. 2018A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillationcited by 110
  5. 2019Personalizing ASR for Dysarthric and Accented Speech with Limited Datacited by 45
  6. 2017Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Modelcited by 37
  7. 2021Conformer-based Hybrid ASR System for Switchboard Datasetcited by 15
  8. 2021Improving Accent Identification and Accented Speech Recognition Under a Framework of Self-supervised Learningcited by 13
  9. 2021E2E-based Multi-task Learning Approach to Joint Speech and Accent Recognitioncited by 12
  10. 2022Layer-wise Fast Adaptation for End-to-End Multi-Accent Speech Recognitioncited by 12
  11. 2022Conformer with dual-mode chunked attention for joint online and offline ASRcited by 10
  12. 2022Confidence Score Based Conformer Speaker Adaptation for Speech Recognitioncited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 0; 2026: 1.

3 papers.

  1. 2024Improving Accented Speech Recognition using Data Augmentation based on Unsupervised Text-to-Speech Synthesiscited by 5
  2. 2024Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognitioncited by 2
  3. 2026Phonetic Modeling of Dialectal Variation in Vietnamese Speechcited by 1