Title :
An Auto-Regressive, Non-Stationary Excited Signal Parameter Estimation Method and an Evaluation of a Singing-Voice Recognition
Author :
Sasou, Akira ; Goto, Masataka ; Hayamizu, Satoru ; Tanaka, Kazuyo
Author_Institution :
Nat. Inst. of Adv. Ind. Sci. & Technol., Japan
fDate :
March 18-23, 2005
Keywords :
autoregressive processes; feature extraction; hidden Markov models; iterative methods; parameter estimation; speech recognition; articulatory system characteristics; auto-regressive hidden Markov model; high-pitched speech; iterative AR-HMM parameter estimation method; nonstationary excitation model; nonstationary excited signal parameter estimation; recognition accuracy; singing voice feature extraction; singing-voice recognition; Feature extraction; Hidden Markov models; Information science; Libraries; Mel frequency cepstral coefficient; Parameter estimation; Signal analysis; Signal resolution; Speech analysis; Speech recognition;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on
Print_ISBN :
0-7803-8874-7
DOI :
10.1109/ICASSP.2005.1415094
