DocumentCode :
3234473
Title :
Quadratic detectors for general nonlinear analysis of speech
Author :
Atlas, Les ; Fang, Jing
Author_Institution :
Dept. of Electr. Eng., Washington Univ., Seattle, WA, USA
Volume :
2
fYear :
1992
fDate :
23-26 Mar 1992
Firstpage :
9
Abstract :
General quadratic detectors are defined and linked to the discrete-time version of Teager´s model (1980), to quadratic (also known as bilinear) time-frequency representations, and to other theory. As demonstrated on speech, these detectors have resolution advantages in simultaneous frequency selectivity and temporal resolution over linear detectors. Preprocessing for pitch detection using the detector is investigated, and it is shown that fast preprocessing for pitch tracking can be obtained by a suitable choice of coefficients. Simple speaker-independent phoneme classification based on a quadratic preprocessor and an artificial neural network is also examined, and comparative results indicate that a quadratic preprocessor facilitates the accurate estimation of waveform features. The preliminary results also suggest that these waveform features may provide useful information for fine phonetic distinctions
Keywords :
neural nets; speech analysis and processing; speech recognition; artificial neural network; bilinear time-frequency representations; fine phonetic distinctions; frequency selectivity; general nonlinear analysis; pitch detection; pitch tracking; quadratic detectors; quadratic preprocessor; quadratic time-frequency representations; speaker-independent phoneme classification; speech analysis; temporal resolution; Artificial neural networks; Band pass filters; Detectors; Equations; Finite impulse response filter; Frequency; Nonlinear filters; Speech analysis; Speech coding; Speech recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1992. ICASSP-92., 1992 IEEE International Conference on
Conference_Location :
San Francisco, CA
ISSN :
1520-6149
Print_ISBN :
0-7803-0532-9
Type :
conf
DOI :
10.1109/ICASSP.1992.226133
Filename :
226133
Link To Document :
بازگشت