Filtering the time sequence of spectral parameters for speaker-independent CDHMM word recognition.
Visualitza/Obre
Estadístiques de LA Referencia / Recolecta
Inclou dades d'ús des de 2022
Cita com:
hdl:2117/102224
Tipus de documentText en actes de congrés
Data publicació1995
EditorESCA - J.M. PARDO, E. ENRIQUEZ, J. ORTEGA, J. FERREIROS GTM-UPM
Condicions d'accésAccés obert
Llevat que s'hi indiqui el contrari, els
continguts d'aquesta obra estan subjectes a la llicència de Creative Commons
:
Reconeixement-NoComercial-SenseObraDerivada 3.0 Espanya
Abstract
In this work, we show how speaker-independent CDHMM word recognition performance can be significantly improved for clean speech by filtering the time sequence of spectral parameters to enhance its time dynamics. Experimental results with the standard TI connected digits database show the filter can achieve more than 30% reduction of string recognition error. As shown in this paper, that improvement is partially due to the speaker variability reduction obtained by attenuating the very low modulation frequencies. The widely used cepstral mean subtraction technique also improves the recognition rate, but it can not achieve such a noticeable improvement as the parameter filter. In fact, the best results are obtained when the peak of the long-term spectrum of the filter output is at around 3 Hz, a frequency which corresponds to the average syllable rate of the employed database.
CitacióNadeu, C., Paches, P., Juang, B. Filtering the time sequence of spectral parameters for speaker-independent CDHMM word recognition.. A: 4th European Conference on Speech Communication and Technology. "Proceedings of the 4th EUROPEAN CONFERENCE ON SPEECH COMMUNICATION AND TECHNOLOGY". Madrid: ESCA - J.M. PARDO, E. ENRIQUEZ, J. ORTEGA, J. FERREIROS GTM-UPM, 1995, p. 923-926.
ISBN1018-4074
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
e95_0923.pdf | 373,8Kb | Visualitza/Obre |