Title :
Usefulness of the Comb Filtering Output for Voiced/Unvoiced Classification and Pitch Detection
Author :
Hu, Hwai-Tsu ; Yu, Chu ; Lin, Chih-Hang
Author_Institution :
Dept. of Electron. Eng., Nat. I-Lan Univ., I-Lan, Taiwan
Abstract :
In this paper, the comb filtering output (CFO) is used to carry out voiced/unvoiced classification along with pitch detection. The usefulness of the CFO consists not only in its measure of periodicity but also in its indication of the pitch period. Given that the voicing detection is achieved by the HMM-based methods using the selected acoustic features as input, the error rate can be brought down to 0.52% in a less rigorous sense. Following the voicing determination, the pitch contour along consecutive voiced frames can be attained using the Viterbi search with the pitch candidates obtained from CFO. The Viterbi search renders a smooth pitch contour that is very appropriate for speech synthesis.
Keywords :
Viterbi detection; comb filters; hidden Markov models; speech processing; HMM-based methods; Viterbi search; comb filtering output; periodicity; pitch detection; selected acoustic features; smooth pitch contour; speech synthesis; voiced/unvoiced classification; voicing detection; Acoustic signal detection; Data mining; Electronic mail; Feature extraction; Filtering; Hidden Markov models; Signal processing; Speech processing; Speech synthesis; Viterbi algorithm; Comb filtering; Hidden Markov model; Pitch estimation.; Voicing/Unvoiced classification;
Conference_Titel :
2009 International Conference on Signal Processing Systems
Conference_Location :
Singapore
Print_ISBN :
978-0-7695-3654-5
DOI :
10.1109/ICSPS.2009.31