Exploring Capabilities of Monolingual Audio Transformers using Large Datasets in Automatic Speech Recognition of Czech

• URL: http://arxiv.org/abs/2206.07627v1
• Date: Wed, 15 Jun 2022 16:14:37 GMT
• Title: Exploring Capabilities of Monolingual Audio Transformers using Large Datasets in Automatic Speech Recognition of Czech
• Authors: Jan Lehe\v{c}ka, Jan \v{S}vec, Ale\v{s} Pra\v{z}\'ak, Josef V. Psutka
• Abstract summary: We present our progress in pretraining Czech monolingual audio transformers from a large dataset containing more than 80 thousand hours of unlabeled speech. We are presenting a large palette of experiments with various fine-tuning setups evaluated on two public datasets.
• Score: 0.9653976364051563
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In this paper, we present our progress in pretraining Czech monolingual audio transformers from a large dataset containing more than 80 thousand hours of unlabeled speech, and subsequently fine-tuning the model on automatic speech recognition tasks using a combination of in-domain data and almost 6 thousand hours of out-of-domain transcribed speech. We are presenting a large palette of experiments with various fine-tuning setups evaluated on two public datasets (CommonVoice and VoxPopuli) and one extremely challenging dataset from the MALACH project. Our results show that monolingual Wav2Vec 2.0 models are robust ASR systems, which can take advantage of large labeled and unlabeled datasets and successfully compete with state-of-the-art LVCSR systems. Moreover, Wav2Vec models proved to be good zero-shot learners when no training data are available for the target ASR task.

Related papers

• Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer [59.57249127943914]
  We present a multilingual Audio-Visual Speech Recognition model incorporating several enhancements to improve performance and audio noise robustness. We increase the amount of audio-visual training data for six distinct languages, generating automatic transcriptions of unlabelled multilingual datasets. Our proposed model achieves new state-of-the-art performance on the LRS3 dataset, reaching WER of 0.8%.
  arXiv  Detail & Related papers  (2024-03-14T01:16:32Z)
• Multi-Sentence Grounding for Long-term Instructional Video [63.27905419718045]
  We aim to establish an automatic, scalable pipeline for denoising a large-scale instructional dataset. We construct a high-quality video-text dataset with multiple descriptive steps supervision, named HowToStep.
  arXiv  Detail & Related papers  (2023-12-21T17:28:09Z)
• 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)
• AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations [88.30635799280923]
  We introduce AV-data2vec which builds audio-visual representations based on predicting contextualized representations. Results on LRS3 show that AV-data2vec consistently outperforms existing methods with the same amount of data and model size.
  arXiv  Detail & Related papers  (2023-02-10T02:55:52Z)
• ON-TRAC Consortium Systems for the IWSLT 2022 Dialect and Low-resource Speech Translation Tasks [8.651248939672769]
  This paper describes the ON-TRAC Consortium translation systems developed for two challenge tracks featured in the Evaluation Campaign of IWSLT 2022: low-resource and dialect speech translation. We build an end-to-end model as our joint primary submission, and compare it against cascaded models that leverage a large fine-tuned wav2vec 2.0 model for ASR. Our results highlight that self-supervised models trained on smaller sets of target data are more effective to low-resource end-to-end ST fine-tuning, compared to large off-the-shelf models.
  arXiv  Detail & Related papers  (2022-05-04T10:36:57Z)
• CI-AVSR: A Cantonese Audio-Visual Speech Dataset for In-car Command Recognition [91.33781557979819]
  We introduce a new dataset, Cantonese In-car Audio-Visual Speech Recognition (CI-AVSR) It consists of 4,984 samples (8.3 hours) of 200 in-car commands recorded by 30 native Cantonese speakers. We provide detailed statistics of both the clean and the augmented versions of our dataset.
  arXiv  Detail & Related papers  (2022-01-11T06:32:12Z)
• Automatic Speech Recognition Datasets in Cantonese Language: A Survey and a New Dataset [85.52036362232688]
  Our dataset consists of 73.6 hours of clean read speech paired with transcripts, collected from Cantonese audiobooks from Hong Kong. It combines philosophy, politics, education, culture, lifestyle and family domains, covering a wide range of topics. We create a powerful and robust Cantonese ASR model by applying multi-dataset learning on MDCC and Common Voice zh-HK.
  arXiv  Detail & Related papers  (2022-01-07T12:09:15Z)

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.