Learning ASR pathways: A sparse multilingual ASR model
Neural network pruning compresses automatic speech recognition (ASR) models effectively. However, in multilingual ASR, language-agnostic pruning may lead to severe performance drops on some languages because language-agnostic pruning masks may not fit all languages and discard important language-specific parameters. In this work, we present ASR pathways, a sparse multilingual ASR model that activates language-specific sub-networks ("pathways"), such that the parameters for each language are learned explicitly. With the overlapping sub-networks, the shared parameters can also enable knowledge transfer for lower-resource languages via joint multilingual training. We propose a novel algorithm to learn ASR pathways, and evaluate the proposed method on 4 languages with a streaming RNN-T model. Our proposed ASR pathways outperform both dense models and a language-agnostically pruned model, and provide better performance on low-resource languages compared to the monolingual sparse models.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Network Pruningspeech-recognitionSpeech RecognitionTransfer LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model
Neural network pruning offers an effective method for compressing a multilingual automatic speech recognition (ASR) model with minimal performance loss. However, it entails several rounds of pruning and re-training neede…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Network Pruningspeech-recognition+1Neural Response Interpretation through the Lens of Critical Pathways
Is critical input information encoded in specific sparse pathways within the neural network? In this work, we discuss the problem of identifying these critical pathways and subsequently leverage them for interpreting the…
From Maxout to Channel-Out: Encoding Information on Sparse Pathways
Motivated by an important insight from neural science, we propose a new framework for understanding the success of the recently proposed "maxout" networks. The framework is based on encoding information on sparse pathway…
General Classificationimage-classificationImage ClassificationOn Model Explanations with Transferable Neural Pathways
Neural pathways as model explanations consist of a sparse set of neurons that provide the same level of prediction performance as the whole model. Existing methods primarily focus on accuracy and sparsity but the generat…
modelLarge vocabulary speech recognition for languages of Africa: multilingual modeling and self-supervised learning
Almost none of the 2,000+ languages spoken in Africa have widely available automatic speech recognition systems, and the required data is also only available for a few languages. We have experimented with two techniques …
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Self-Supervised Learningspeech-recognition+1