Title :
Phone-dependent channel compensated hidden Markov model for telephone speech recognition
Author :
Chien, Jen-Tzung ; Wang, Hsiao-Chuan
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan
fDate :
6/1/1998 12:00:00 AM
Abstract :
We propose the phone-dependent channel compensated hidden Markov model (PDCC-HMM) for telephone speech recognition. The PDCC-HMM is derived by modifying the conventional hidden Markov model (HMM) with the phone-dependent channel compensation vectors. The telephone speech is recognized efficiently by using the derived PDCC-HMM. Experiments demonstrate the robustness of PDCC-HMM in speech recognition and show the significant reduction of recognition error rate by 50% compared to the conventional HMM method.
Keywords :
compensation; hidden Markov models; speech recognition; telephony; PDCC-HMM; hidden Markov model; phone-dependent channel compensation vectors; robustness; telephone speech recognition; Associate members; Automatic speech recognition; Cepstral analysis; Error analysis; Hidden Markov models; Robustness; Signal processing algorithms; Speech enhancement; Speech recognition; Telephony;
Journal_Title :
Signal Processing Letters, IEEE