A comparison of signal processing front ends for automatic word recognition
- 1 July 1995
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Speech and Audio Processing
- Vol. 3 (4) , 286-293
- https://doi.org/10.1109/89.397093
Abstract
This paper compares the word error rate of a speech recognizer using several signal processing front ends based on auditory properties. Front ends were compared with a control mel filter bank (MFB) based cepstral front end in clean speech and with speech degraded by noise and spectral variability, using the TI-105 isolated word database. MFB recognition error rates ranged from 0.5 to 26.9% in noise, depending on the SNR, and auditory models provided error rates as much as four percentage points lower. With speech degraded by linear filtering, MFB error rates ranged from 0.5 to 3.1%, and the reduction in error rates provided by auditory models was less than 0.5 percentage points. Some earlier studies that demonstrated considerably more improvement with auditory models used linear predictive coding (LPC) based control front ends. This paper shows that MFB cepstra significantly outperform LPC cepstra under noisy conditions. Techniques using an optimal linear combination of features for data reduction were also evaluated.<>Keywords
This publication has 11 references indexed in Scilit:
- Multi-style training for robust isolated-word speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Recognition of speech under stress and in noisePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A computational model for the peripheral auditory system: Application of speech recognition researchPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A comparison of several acoustic representations for speech recognition with degraded and undegraded speechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- The design for the wall street journal-based CSR corpusPublished by Association for Computational Linguistics (ACL) ,1992
- Multiple approaches to robust speech recognitionPublished by Association for Computational Linguistics (ACL) ,1992
- Speech coding in the auditory nerve: I. Vowel-like soundsThe Journal of the Acoustical Society of America, 1984
- Encoding of steady-state vowels in the auditory nerve: Representation in terms of discharge rateThe Journal of the Acoustical Society of America, 1979
- Frequency discrimination in the auditory system: Place or periodicity mechanisms?Proceedings of the IEEE, 1970
- Analog Measurements of Sound Radiation from the MouthThe Journal of the Acoustical Society of America, 1960