Syllable based DNN-HMM Cantonese Speech to Text System

TL;DR

This paper presents a Cantonese speech-to-text system using syllable-based DNN-HMM models, demonstrating improved accuracy and efficiency, aimed at assisting dyslexic students with speech recognition despite intra-syllable variations.

Contribution

The study introduces a syllable-based acoustic modeling approach for Cantonese STT, comparing IF and ONC units, and incorporates I-vector speaker adaptation to enhance performance.

Findings

ONC-based syllable modeling with I-vector adaptation achieves lowest WER of 9.66%

System demonstrates real-time processing with RTF of 1.38812

Syllable units effectively capture intra-syllable variations in Cantonese

Abstract

This paper reports our work on building up a Cantonese Speech-to-Text (STT) system with a syllable based acoustic model. This is a part of an effort in building a STT system to aid dyslexic students who have cognitive deficiency in writing skills but have no problem expressing their ideas through speech. For Cantonese speech recognition, the basic unit of acoustic models can either be the conventional Initial-Final (IF) syllables, or the Onset-Nucleus-Coda (ONC) syllables where finals are further split into nucleus and coda to reflect the intra-syllable variations in Cantonese. By using the Kaldi toolkit, our system is trained using the stochastic gradient descent optimization model with the aid of GPUs for the hybrid Deep Neural Network and Hidden Markov Model (DNN-HMM) with and without I-vector based speaker adaptive training technique. The input features of the same Gaussian Mixture Model with speaker adaptive training (GMM-SAT) to DNN are used in all cases. Experiments show that the ONC-based syllable acoustic modeling with I-vector based DNN-HMM achieves the best performance with the word error rate (WER) of 9.66% and the real time factor (RTF) of 1.38812.