Exploring SSL Discrete Tokens for Multilingual ASR

• URL: http://arxiv.org/abs/2409.08805v1
• Date: Fri, 13 Sep 2024 13:13:39 GMT
• Title: Exploring SSL Discrete Tokens for Multilingual ASR
• Authors: Mingyu Cui, Daxin Tan, Yifan Yang, Dingdong Wang, Huimeng Wang, Xiao Chen, Xie Chen, Xunying Liu,
• Abstract summary: This study presents a comparison of discrete tokens generated by various leading SSL models across multiple language domains. Experimental results demonstrate that discrete tokens achieve comparable results against systems trained on Fbank features in ASR tasks.
• Score: 29.059205486691745
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the advancement of Self-supervised Learning (SSL) in speech-related tasks, there has been growing interest in utilizing discrete tokens generated by SSL for automatic speech recognition (ASR), as they offer faster processing techniques. However, previous studies primarily focused on multilingual ASR with Fbank features or English ASR with discrete tokens, leaving a gap in adapting discrete tokens for multilingual ASR scenarios. This study presents a comprehensive comparison of discrete tokens generated by various leading SSL models across multiple language domains. We aim to explore the performance and efficiency of speech discrete tokens across multiple language domains for both monolingual and multilingual ASR scenarios. Experimental results demonstrate that discrete tokens achieve comparable results against systems trained on Fbank features in ASR tasks across seven language domains with an average word error rate (WER) reduction of 0.31% and 1.76% absolute (2.80% and 15.70% relative) on dev and test sets respectively, with particularly WER reduction of 6.82% absolute (41.48% relative) on the Polish test set.

Related papers

• Enhancing Multilingual ASR for Unseen Languages via Language Embedding Modeling [50.62091603179394]
  Whisper, one of the most advanced ASR models, handles 99 languages effectively. However, Whisper struggles with unseen languages, those not included in its pre-training. We propose methods that exploit these relationships to enhance ASR performance on unseen languages.
  arXiv  Detail & Related papers  (2024-12-21T04:05:43Z)
• Improving Multilingual ASR in the Wild Using Simple N-best Re-ranking [68.77659513993507]
  We present a simple and effective N-best re-ranking approach to improve multilingual ASR accuracy. Our results show spoken language identification accuracy improvements of 8.7% and 6.1%, respectively, and word error rates which are 3.3% and 2.0% lower on these benchmarks.
  arXiv  Detail & Related papers  (2024-09-27T03:31:32Z)
• Unlikelihood Tuning on Negative Samples Amazingly Improves Zero-Shot Translation [79.96416609433724]
  Zero-shot translation (ZST) aims to translate between unseen language pairs in training data. The common practice to guide the zero-shot language mapping during inference is to deliberately insert the source and target language IDs. Recent studies have shown that language IDs sometimes fail to navigate the ZST task, making them suffer from the off-target problem.
  arXiv  Detail & Related papers  (2023-09-28T17:02:36Z)
• Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages [76.95115818308918]
  We introduce the Universal Speech Model (USM), a single large model that performs automatic speech recognition (ASR) across 100+ languages. This is achieved by pre-training the encoder of the model on a large unlabeled multilingual dataset of 12 million (M) hours spanning over 300 languages. We use multilingual pre-training with random-projection quantization and speech-text modality matching to achieve state-of-the-art performance on downstream multilingual ASR and speech-to-text translation tasks.
  arXiv  Detail & Related papers  (2023-03-02T07:47:18Z)
• 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)
• Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities [35.15674061731237]
  This paper explores large-scale multilingual ASR models on 70 languages. We show that our multilingual ASR generalizes well on an unseen dataset and domain, achieving 9.5% and 7.5% WER on Multilingual Librispeech (MLS) with zero-shot and finetuning, respectively.
  arXiv  Detail & Related papers  (2022-11-10T18:43:42Z)
• Bilingual End-to-End ASR with Byte-Level Subwords [4.268218327369146]
  We study different representations including character-level, byte-level, byte pair encoding (BPE), and byte-level byte pair encoding (BBPE) We focus on developing a single end-to-end model to support utterance-based bilingual ASR, where speakers do not alternate between two languages in a single utterance but may change languages across utterances. We find that BBPE with penalty schemes can improve utterance-based bilingual ASR performance by 2% to 5% relative even with smaller number of outputs and fewer parameters.
  arXiv  Detail & Related papers  (2022-05-01T15:01:01Z)
• Multilingual Speech Recognition using Knowledge Transfer across Learning Processes [15.927513451432946]
  Experimental results reveal the best pre-training strategy resulting in 3.55% relative reduction in overall WER. A combination of LEAP and SSL yields 3.51% relative reduction in overall WER when using language ID.
  arXiv  Detail & Related papers  (2021-10-15T07:50:27Z)
• Is Attention always needed? A Case Study on Language Identification from Speech [1.162918464251504]
  The present study introduces convolutional recurrent neural network (CRNN) based LID. CRNN based LID is designed to operate on the Mel-frequency Cepstral Coefficient (MFCC) characteristics of audio samples. The LID model exhibits high-performance levels ranging from 97% to 100% for languages that are linguistically similar.
  arXiv  Detail & Related papers  (2021-10-05T16:38:57Z)
• 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)
• 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.