Token-Level Ensemble Distillation for Grapheme-to-Phoneme Conversion

by   Hao Sun, et al.
Peking University

Grapheme-to-phoneme (G2P) conversion is an important task in automatic speech recognition and text-to-speech systems. Recently, G2P conversion is viewed as a sequence to sequence task and modeled by RNN or CNN based encoder-decoder framework. However, previous works do not consider the practical issues when deploying G2P model in the production system, such as how to leverage additional unlabeled data to boost the accuracy, as well as reduce model size for online deployment. In this work, we propose token-level ensemble distillation for G2P conversion, which can (1) boost the accuracy by distilling the knowledge from additional unlabeled data, and (2) reduce the model size but maintain the high accuracy, both of which are very practical and helpful in the online production system. We use token-level knowledge distillation, which results in better accuracy than the sequence-level counterpart. What is more, we adopt the Transformer instead of RNN or CNN based models to further boost the accuracy of G2P conversion. Experiments on the publicly available CMUDict dataset and an internal English dataset demonstrate the effectiveness of our proposed method. Particularly, our method achieves 19.88 dataset, outperforming the previous works by more than 4.22 the new state-of-the-art results.


page 1

page 2

page 3

page 4


Pretraining Techniques for Sequence-to-Sequence Voice Conversion

Sequence-to-sequence (seq2seq) voice conversion (VC) models are attracti...

Alignment Knowledge Distillation for Online Streaming Attention-based Speech Recognition

This article describes an efficient training method for online streaming...

Efficient Knowledge Distillation for RNN-Transducer Models

Knowledge Distillation is an effective method of transferring knowledge ...

Transformer based Grapheme-to-Phoneme Conversion

Attention mechanism is one of the most successful techniques in deep lea...

A Deep Investigation of RNN and Self-attention for the Cyrillic-Traditional Mongolian Bidirectional Conversion

Cyrillic and Traditional Mongolian are the two main members of the Mongo...

LiteG2P: A fast, light and high accuracy model for grapheme-to-phoneme conversion

As a key component of automated speech recognition (ASR) and the front-e...

Knowledge Distilled Ensemble Model for sEMG-based Silent Speech Interface

Voice disorders affect millions of people worldwide. Surface electromyog...

Please sign up or login with your details

Forgot password? Click here to reset