From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition

• URL: http://arxiv.org/abs/2301.07851v1
• Date: Thu, 19 Jan 2023 02:37:56 GMT
• Title: From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition
• Authors: Chao-Han Huck Yang, Bo Li, Yu Zhang, Nanxin Chen, Rohit Prabhavalkar, Tara N. Sainath, Trevor Strohman
• Abstract summary: 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.
• Score: 50.93943755401025
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we propose a new parameter-efficient learning framework based on neural model reprogramming for cross-lingual speech recognition, which can \textbf{re-purpose} well-trained English automatic speech recognition (ASR) models to recognize the other languages. We design different auxiliary neural architectures focusing on learnable pre-trained feature enhancement that, for the first time, empowers model reprogramming on ASR. Specifically, we investigate how to select trainable components (i.e., encoder) of a conformer-based RNN-Transducer, as a frozen pre-trained backbone. Experiments on a seven-language multilingual LibriSpeech speech (MLS) task show that model reprogramming only requires 4.2% (11M out of 270M) to 6.8% (45M out of 660M) of its original trainable parameters from a full ASR model to perform competitive results in a range of 11.9% to 8.1% WER averaged across different languages. In addition, we discover different setups to make large-scale pre-trained ASR succeed in both monolingual and multilingual speech recognition. Our methods outperform existing ASR tuning architectures and their extension with self-supervised losses (e.g., w2v-bert) in terms of lower WER and better training efficiency.

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)
• Unified model for code-switching speech recognition and language identification based on a concatenated tokenizer [17.700515986659063]
  Code-Switching (CS) multilingual Automatic Speech Recognition (ASR) models can transcribe speech containing two or more alternating languages during a conversation. This paper proposes a new method for creating code-switching ASR datasets from purely monolingual data sources. A novel Concatenated Tokenizer enables ASR models to generate language ID for each emitted text token while reusing existing monolingual tokenizers.
  arXiv  Detail & Related papers  (2023-06-14T21:24:11Z)
• 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)
• Learning ASR pathways: A sparse multilingual ASR model [31.147484652643282]
  We present ASR pathways, a sparse multilingual ASR model that activates language-specific sub-networks ("pathways") With the overlapping sub-networks, the shared parameters can also enable knowledge transfer for lower-resource languages via joint multilingual training. Our proposed ASR pathways outperform both dense models and a language-agnostically pruned model, and provide better performance on low-resource languages.
  arXiv  Detail & Related papers  (2022-09-13T05:14:08Z)
• Adaptive Activation Network For Low Resource Multilingual Speech Recognition [30.460501537763736]
  We introduce an adaptive activation network to the upper layers of ASR model. We also proposed two approaches to train the model: (1) cross-lingual learning, replacing the activation function from source language to target language, and (2) multilingual learning. Our experiments on IARPA Babel datasets demonstrated that our approaches outperform the from-scratch training and traditional bottleneck feature based methods.
  arXiv  Detail & Related papers  (2022-05-28T04:02:59Z)
• 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)
• 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)
• 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)
• Improving Cross-Lingual Transfer Learning for End-to-End Speech Recognition with Speech Translation [63.16500026845157]
  We introduce speech-to-text translation as an auxiliary task to incorporate additional knowledge of the target language. We show that training ST with human translations is not necessary. Even with pseudo-labels from low-resource MT (200K examples), ST-enhanced transfer brings up to 8.9% WER reduction to direct transfer.
  arXiv  Detail & Related papers  (2020-06-09T19:34:11Z)

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.