Multistage Fine-tuning Strategies for Automatic Speech Recognition in Low-resource Languages

• URL: http://arxiv.org/abs/2411.04573v1
• Date: Thu, 07 Nov 2024 09:57:57 GMT
• Title: Multistage Fine-tuning Strategies for Automatic Speech Recognition in Low-resource Languages
• Authors: Leena G Pillai, Kavya Manohar, Basil K Raju, Elizabeth Sherly,
• Abstract summary: This paper presents a novel multistage fine-tuning strategy designed to enhance automatic speech recognition (ASR) performance in low-resource languages. In this approach we aim to build ASR model for languages with limited digital resources by sequentially adapting the model across linguistically similar languages. We experimented this on the Malasar language, a Dravidian language spoken by approximately ten thousand people in the Western Ghats of South India.
• Score: 0.0
• License:
• Abstract: This paper presents a novel multistage fine-tuning strategy designed to enhance automatic speech recognition (ASR) performance in low-resource languages using OpenAI's Whisper model. In this approach we aim to build ASR model for languages with limited digital resources by sequentially adapting the model across linguistically similar languages. We experimented this on the Malasar language, a Dravidian language spoken by approximately ten thousand people in the Western Ghats of South India. Malasar language faces critical challenges for technological intervention due to its lack of a native script and absence of digital or spoken data resources. Working in collaboration with Wycliffe India and Malasar community members, we created a spoken Malasar corpus paired with transcription in Tamil script, a closely related major language. In our approach to build ASR model for Malasar, we first build an intermediate Tamil ASR, leveraging higher data availability for Tamil annotated speech. This intermediate model is subsequently fine-tuned on Malasar data, allowing for more effective ASR adaptation despite limited resources. The multistage fine-tuning strategy demonstrated significant improvements over direct fine-tuning on Malasar data alone, achieving a word error rate (WER) of 51.9%, which is 4.5% absolute reduction when compared to the direct fine-tuning method. Further a WER reduction to 47.3% was achieved through punctuation removal in post-processing, which addresses formatting inconsistencies that impact evaluation. Our results underscore the effectiveness of sequential multistage fine-tuning combined with targeted post-processing as a scalable strategy for ASR system development in low-resource languages, especially where linguistic similarities can be leveraged to bridge gaps in training data.

Related papers

• Weighted Cross-entropy for Low-Resource Languages in Multilingual Speech Recognition [2.7247388777405597]
  We introduce a novel application of weighted cross-entropy, typically used for unbalanced datasets. We fine-tune the Whisper multilingual ASR model on five high-resource languages and one low-resource language.
  arXiv  Detail & Related papers  (2024-09-25T14:09:09Z)
• Meta-Whisper: Speech-Based Meta-ICL for ASR on Low-Resource Languages [51.12146889808824]
  Meta-Whisper is a novel approach to improve automatic speech recognition for low-resource languages. It enhances Whisper's ability to recognize speech in unfamiliar languages without extensive fine-tuning.
  arXiv  Detail & Related papers  (2024-09-16T16:04:16Z)
• A Novel Self-training Approach for Low-resource Speech Recognition [15.612232220719653]
  We propose a self-training approach for automatic speech recognition (ASR) for low-resource settings. Our approach significantly improves word error rate, achieving a relative improvement of 14.94%. Our proposed approach reports the best results on the Common Voice Punjabi dataset.
  arXiv  Detail & Related papers  (2023-08-10T01:02:45Z)
• Model Adaptation for ASR in low-resource Indian Languages [28.02064068964355]
  Automatic speech recognition (ASR) performance has improved drastically in recent years, mainly enabled by self-supervised learning (SSL) based acoustic models like wav2vec2 and large-scale multi-lingual training like Whisper. A huge challenge still exists for low-resource languages where the availability of both audio and text is limited. This is where a lot of adaptation and fine-tuning techniques can be applied to overcome the low-resource nature of the data by utilising well-resourced similar languages. It could be the case that an abundance of acoustic data in a language reduces the need for large text-only corpora
  arXiv  Detail & Related papers  (2023-07-16T05:25:51Z)
• No Language Left Behind: Scaling Human-Centered Machine Translation [69.28110770760506]
  We create datasets and models aimed at narrowing the performance gap between low and high-resource languages. We propose multiple architectural and training improvements to counteract overfitting while training on thousands of tasks. Our model achieves an improvement of 44% BLEU relative to the previous state-of-the-art.
  arXiv  Detail & Related papers  (2022-07-11T07:33:36Z)
• Non-Linear Pairwise Language Mappings for Low-Resource Multilingual Acoustic Model Fusion [26.728287476234538]
  hybrid DNN-HMM acoustic models fusion is proposed in a multilingual setup for the low-resource languages. Posterior distributions from different monolingual acoustic models against a target language speech signal are fused together. A separate regression neural network is trained for each source-target language pair to transform posteriors from source acoustic model to the target language.
  arXiv  Detail & Related papers  (2022-07-07T15:56:50Z)
• Cross-Lingual Text Classification of Transliterated Hindi and Malayalam [31.86825573676501]
  We combine data augmentation approaches with a Teacher-Student training scheme to address this issue. We evaluate our method on transliterated Hindi and Malayalam, also introducing new datasets for benchmarking on real-world scenarios. Our method yielded an average improvement of +5.6% on mBERT and +4.7% on XLM-R in F1 scores over their strong baselines.
  arXiv  Detail & Related papers  (2021-08-31T05:13:17Z)
• Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation [105.41167108465085]
  Cross-lingual Machine Reading (CLMRC) remains a challenging problem due to the lack of large-scale datasets in low-source languages. We propose a novel augmentation approach named Language Branch Machine Reading (LBMRC) LBMRC trains multiple machine reading comprehension (MRC) models proficient in individual language. We devise a multilingual distillation approach to amalgamate knowledge from multiple language branch models to a single model for all target languages.
  arXiv  Detail & Related papers  (2020-10-27T13:12:17Z)
• How Phonotactics Affect Multilingual and Zero-shot ASR Performance [74.70048598292583]
  A Transformer encoder-decoder model has been shown to leverage multilingual data well in IPA transcriptions of languages presented during training. We replace the encoder-decoder with a hybrid ASR system consisting of a separate AM and LM. We show that the gain from modeling crosslingual phonotactics is limited, and imposing a too strong model can hurt the zero-shot transfer.
  arXiv  Detail & Related papers  (2020-10-22T23:07:24Z)
• 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)
• Joint Contextual Modeling for ASR Correction and Language Understanding [60.230013453699975]
  We propose multi-task neural approaches to perform contextual language correction on ASR outputs jointly with language understanding (LU) We show that the error rates of off the shelf ASR and following LU systems can be reduced significantly by 14% relative with joint models trained using small amounts of in-domain data.
  arXiv  Detail & Related papers  (2020-01-28T22:09:25Z)

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.