A new SCHMM/MNN hybrid model for mandarin speech recognition

Shin Lun Tung, Yau Tarng Juang

Research output: Contribution to journalArticlepeer-review


In this paper, we propose a new scheme that combines the semi-continuous hidden Markov model (SCHMM) and modular neural networks (MNN) to recognize isolated Mandarin syllables. The SCHMM formulation has been proven successful in modeling the temporal arrangement of speech signals, and MNN is also suitable for performing static pattern classification. In the scheme described here, SCHMM outputs establish the sequence of observation vectors to be inputs of the MNN. Experimental results show that by combining both the discriminative power of MNN and the capability of modeling the temporal variations of an SCHMM into a hybrid model, speech recognition performance is significantly improved.

Original languageEnglish
Pages (from-to)355-365
Number of pages11
JournalJournal of Information Science and Engineering
Issue number2
StatePublished - 1997


  • Fine classification
  • Mandarin speech recognition
  • Parallel distribution processing
  • Semi-continuous hidden Markov model


Dive into the research topics of 'A new SCHMM/MNN hybrid model for mandarin speech recognition'. Together they form a unique fingerprint.

Cite this