XLS-R Deep Learning Model for Multilingual ASR on Low- Resource Languages: Indonesian, Javanese, and Sundanese

• URL: http://arxiv.org/abs/2401.06832v1
• Date: Fri, 12 Jan 2024 13:44:48 GMT
• Title: XLS-R Deep Learning Model for Multilingual ASR on Low- Resource Languages: Indonesian, Javanese, and Sundanese
• Authors: Panji Arisaputra, Alif Tri Handoyo and Amalia Zahra
• Abstract summary: The study aims to improve ASR performance in converting spoken language into written text, specifically for Indonesian, Javanese, and Sundanese languages. The results show that the XLS-R 300m model achieves competitive Word Error Rate (WER) measurements, with a slight compromise in performance for Javanese and Sundanese languages.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: This research paper focuses on the development and evaluation of Automatic Speech Recognition (ASR) technology using the XLS-R 300m model. The study aims to improve ASR performance in converting spoken language into written text, specifically for Indonesian, Javanese, and Sundanese languages. The paper discusses the testing procedures, datasets used, and methodology employed in training and evaluating the ASR systems. The results show that the XLS-R 300m model achieves competitive Word Error Rate (WER) measurements, with a slight compromise in performance for Javanese and Sundanese languages. The integration of a 5-gram KenLM language model significantly reduces WER and enhances ASR accuracy. The research contributes to the advancement of ASR technology by addressing linguistic diversity and improving performance across various languages. The findings provide insights into optimizing ASR accuracy and applicability for diverse linguistic contexts.

Related papers

• Romanization Encoding For Multilingual ASR [17.296868524096986]
  We introduce romanization encoding for script-heavy languages to optimize multilingual and code-switching Automatic Speech Recognition systems. By adopting romanization encoding alongside a balanced tokenizer within a FastConformer-RNNT framework equipped with a Roman2Char module, we significantly reduce vocabulary and output dimensions. Our method decouples acoustic modeling and language modeling, enhancing the flexibility and adaptability of the system.
  arXiv  Detail & Related papers  (2024-07-05T09:13:24Z)
• Speech Emotion Recognition with ASR Transcripts: A Comprehensive Study on Word Error Rate and Fusion Techniques [17.166092544686553]
  This study benchmarks Speech Emotion Recognition using ASR transcripts with varying Word Error Rates (WERs) on well-known corpora. We propose a unified ASR error-robust framework integrating ASR error correction and modality-gated fusion, achieving lower WER and higher SER results.
  arXiv  Detail & Related papers  (2024-06-12T15:59:25Z)
• Enabling ASR for Low-Resource Languages: A Comprehensive Dataset Creation Approach [0.6445605125467574]
  This study introduces a novel pipeline designed to generate ASR training datasets from audiobooks. The common structure of these audiobooks poses a unique challenge due to the extensive length of audio segments. We propose a method for effectively aligning audio with its corresponding text and segmenting it into lengths suitable for ASR training.
  arXiv  Detail & Related papers  (2024-06-03T15:38:40Z)
• Strategies for improving low resource speech to text translation relying on pre-trained ASR models [59.90106959717875]
  This paper presents techniques and findings for improving the performance of low-resource speech to text translation (ST) We conducted experiments on both simulated and real-low resource setups, on language pairs English - Portuguese, and Tamasheq - French respectively.
  arXiv  Detail & Related papers  (2023-05-31T21:58:07Z)
• 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)
• Data Augmentation for Low-Resource Quechua ASR Improvement [2.260916274164351]
  Deep learning methods have made it possible to deploy systems with word error rates below 5% for ASR of English. For so-called low-resource languages, methods of creating new resources on the basis of existing ones are being investigated. We describe our data augmentation approach to improve the results of ASR models for low-resource and agglutinative languages.
  arXiv  Detail & Related papers  (2022-07-14T12:49:15Z)
• ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion [49.617722668505834]
  We show that our approach permits the application of speech synthesis and voice conversion to improve ASR systems using only one target-language speaker during model training. It is possible to obtain promising ASR training results with our data augmentation method using only a single real speaker in a target language.
  arXiv  Detail & Related papers  (2022-03-29T11:55:30Z)
• LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech [63.84741259993937]
  Self-Supervised Learning (SSL) using huge unlabeled data has been successfully explored for image and natural language processing. Recent works also investigated SSL from speech. We propose LeBenchmark: a reproducible framework for assessing SSL from speech.
  arXiv  Detail & Related papers  (2021-04-23T08:27:09Z)
• Arabic Speech Recognition by End-to-End, Modular Systems and Human [56.96327247226586]
  We perform a comprehensive benchmarking for end-to-end transformer ASR, modular HMM-DNN ASR, and human speech recognition. For ASR the end-to-end work led to 12.5%, 27.5%, 23.8% WER; a new performance milestone for the MGB2, MGB3, and MGB5 challenges respectively. Our results suggest that human performance in the Arabic language is still considerably better than the machine with an absolute WER gap of 3.6% on average.
  arXiv  Detail & Related papers  (2021-01-21T05:55:29Z)
• LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition [148.43282526983637]
  We develop LRSpeech, a TTS and ASR system for languages with low data cost. We conduct experiments on an experimental language (English) and a truly low-resource language (Lithuanian) to verify the effectiveness of LRSpeech. We are currently deploying LRSpeech into a commercialized cloud speech service to support TTS on more rare languages.
  arXiv  Detail & Related papers  (2020-08-09T08:16:33Z)

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.