HMM-Based speech recognition using adaptive framing
Document Type
Conference Item
Publication Date
1-1-2009
Abstract
A common approach in mapping a signal to discrete events is to define a set of symbols that correspond to useful acoustic features of the signal over a short constant time interval. This paper proposes a Hidden Markov Models (HMM) based speech recognition by using cepstrum feature of the signal over adaptive time interval. First pitch period is detected by dyadic wavelet transform and divides the voiced speech signal according to the detected period. Then, system performs HMM-based speech recognition using cepstrum feature to classify the speech signals. Two speech recognition systems have been developed, one is based on constant time framing and the other is adaptive framing. The results are compared and found that adaptive framing method shows better result in both data distribution and recognition rate.
Keywords
Speech Recognition, HMM-based, Adaptive Time Intervals
Divisions
fac_eng
Event Title
IEEE Region 10 Conference 2009
Event Location
Singapore
Event Dates
NOV 23-26, 2009
Event Type
conference
Additional Information
Univ Malaya, Dept Elect Engn, Kuala Lumpur 50603, Malaysia