Syllable based DNN-HMM Cantonese speech to text system

T.C.T. Wong, W.Y.C. Li, W.H. Chiu, Qin Lu, M. Li, D. Xiong, S. Yu, Vincent To Yee Ng

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review


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.
Original languageEnglish
Title of host publicationProceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016
PublisherEuropean Language Resources Association (ELRA)
Number of pages7
ISBN (Electronic)9782951740891
Publication statusPublished - 2016
EventInternational Conference on Language Resources and Evaluation [LREC] -
Duration: 1 Jan 2016 → …


ConferenceInternational Conference on Language Resources and Evaluation [LREC]
Period1/01/16 → …


  • Cantonese speech recognition
  • Onset-Nucleus-Coda Syllable Scheme
  • Kaldi toolkit


Dive into the research topics of 'Syllable based DNN-HMM Cantonese speech to text system'. Together they form a unique fingerprint.

Cite this