Leveraging LLM and Self-Supervised Training Models for Speech Recognition in Chinese Dialects: A Comparative Analysis

• URL: http://arxiv.org/abs/2505.21138v2
• Date: Mon, 16 Jun 2025 07:57:48 GMT
• Title: Leveraging LLM and Self-Supervised Training Models for Speech Recognition in Chinese Dialects: A Comparative Analysis
• Authors: Tianyi Xu, Hongjie Chen, Wang Qing, Lv Hang, Jian Kang, Li Jie, Zhennan Lin, Yongxiang Li, Xie Lei,
• Abstract summary: Self-supervised pre-training, combined with large language models (LLM), can effectively enhance ASR performance in low-resource scenarios.<n>We pre-train a Data2vec2 model on 300,000 hours of unlabeled dialect and accented speech data and do alignment training on a supervised dataset of 40,000 hours.
• Score: 4.774607166378613
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large-scale training corpora have significantly improved the performance of ASR models. Unfortunately, due to the relative scarcity of data, Chinese accents and dialects remain a challenge for most ASR models. Recent advancements in self-supervised learning have shown that self-supervised pre-training, combined with large language models (LLM), can effectively enhance ASR performance in low-resource scenarios. We aim to investigate the effectiveness of this paradigm for Chinese dialects. Specifically, we pre-train a Data2vec2 model on 300,000 hours of unlabeled dialect and accented speech data and do alignment training on a supervised dataset of 40,000 hours. Then, we systematically examine the impact of various projectors and LLMs on Mandarin, dialect, and accented speech recognition performance under this paradigm. Our method achieved SOTA results on multiple dialect datasets, including Kespeech. We will open-source our work to promote reproducible research

Related papers

• A Practitioner's Guide to Building ASR Models for Low-Resource Languages: A Case Study on Scottish Gaelic [9.380879437204277]
  An effective approach to the development of ASR systems for low-resource languages is to fine-tune an existing multilingual end-to-end model.<n>We show that an approach combining hybrid HMMs with self-supervised models can yield substantially better performance with limited training data.<n>We benchmark our approach on Scottish Gaelic, achieving WER reductions of 32% relative over our best fine-tuned Whisper model.
  arXiv  Detail & Related papers  (2025-06-05T11:52:08Z)
• Zero-resource Speech Translation and Recognition with LLMs [38.11535502039386]
  We propose to leverage a multilingual Large Language Model (LLM) to perform ST and ASR in languages for which the model has never seen paired audio-text data.<n>We achieve this by using a pre-trained multilingual speech encoder, a multilingual LLM, and a lightweight adaptation module that maps the audio representations to the token embedding space of the LLM.
  arXiv  Detail & Related papers  (2024-12-24T17:37:11Z)
• Automatic Speech Recognition for the Ika Language [0.0]
  We fine-tune the pretrained wav2vec 2.0 Massively translations Speech Models on a high-quality speech dataset compiled from New Testament Bible Multilingual in Ika. Our results show that fine-tuning multilingual pretrained models achieves a Word Error Rate (WER) of 0.5377 and Character Error Rate (CER) of 0.2651 with just over 1 hour of training data.
  arXiv  Detail & Related papers  (2024-10-01T11:56:42Z)
• Performance Analysis of Speech Encoders for Low-Resource SLU and ASR in Tunisian Dialect [11.013934239276036]
  Speech encoders pretrained through self-supervised learning (SSL) have demonstrated remarkable performance in various downstream tasks. This paper contributes by comparing the effectiveness of SSL approaches in the context of the low-resource spoken Tunisian Arabic dialect.
  arXiv  Detail & Related papers  (2024-07-05T14:21:36Z)
• Reduce, Reuse, Recycle: Is Perturbed Data better than Other Language augmentation for Low Resource Self-Supervised Speech Models [48.44820587495038]
  Self-supervised representation learning (SSRL) has demonstrated superior performance than supervised models for tasks including phoneme recognition. Training SSRL models poses a challenge for low-resource languages where sufficient pre-training data may not be available. We propose to use audio augmentation techniques, namely: pitch variation, noise addition, accented target language and other language speech to pre-train SSRL models in a low resource condition and evaluate phoneme recognition.
  arXiv  Detail & Related papers  (2023-09-22T10:09:09Z)
• Mispronunciation detection using self-supervised speech representations [10.010024759851142]
  We study the use of SSL models for the task of mispronunciation detection for second language learners. We compare two downstream approaches: 1) training the model for phone recognition using native English data, and 2) training a model directly for the target task using non-native English data.
  arXiv  Detail & Related papers  (2023-07-30T21:20:58Z)
• Learning Cross-lingual Visual Speech Representations [108.68531445641769]
  Cross-lingual self-supervised visual representation learning has been a growing research topic in the last few years. We use the recently-proposed Raw Audio-Visual Speechs (RAVEn) framework to pre-train an audio-visual model with unlabelled data. Our experiments show that: (1) multi-lingual models with more data outperform monolingual ones, but, when keeping the amount of data fixed, monolingual models tend to reach better performance.
  arXiv  Detail & Related papers  (2023-03-14T17:05:08Z)
• From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition [50.93943755401025]
  We propose a new parameter-efficient learning framework based on neural model reprogramming for cross-lingual speech recognition. We design different auxiliary neural architectures focusing on learnable pre-trained feature enhancement. Our methods outperform existing ASR tuning architectures and their extension with self-supervised losses.
  arXiv  Detail & Related papers  (2023-01-19T02:37:56Z)
• WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing [102.45426364965887]
  We propose a new pre-trained model, WavLM, to solve full-stack downstream speech tasks. WavLM is built based on the HuBERT framework, with an emphasis on both spoken content modeling and speaker identity preservation. We scale up the training dataset from 60k hours to 94k hours of public audio data, and optimize its training procedure for better representation extraction.
  arXiv  Detail & Related papers  (2021-10-26T17:55:19Z)
• UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training [72.004873454347]
  Two methods are introduced for enhancing the unsupervised speaker information extraction. Experiment results on SUPERB benchmark show that the proposed system achieves state-of-the-art performance. We scale up training dataset to 94 thousand hours public audio data and achieve further performance improvement.
  arXiv  Detail & Related papers  (2021-10-12T05:43:30Z)
• Unsupervised Cross-lingual Representation Learning for Speech Recognition [63.85924123692923]
  XLSR learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages. We build on wav2vec 2.0 which is trained by solving a contrastive task over masked latent speech representations. Experiments show that cross-lingual pretraining significantly outperforms monolingual pretraining.
  arXiv  Detail & Related papers  (2020-06-24T18:25:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.