Title :
Noise compensation for speech recognition in car noise environments
Author :
Yang, Ruikang ; Haavisto, Patri
Author_Institution :
Nokia Res. Center, Tampere, Finland
Abstract :
A noise compensation algorithm for HMM based speech recognition systems, which utilizes the parallel model combination concept, is presented. The algorithm was tested using the TIDIGITS database with artificially added car noise. Very promising results were obtained. The results show that at -10 dB SNR the recognition accuracy could be improved from 34% to 89%. The noise compensation algorithm was also tested using a database which was recorded in a car. Improved performance was obtained, but the improvement; was clearly smaller than with the artificially added noise
Keywords :
Gaussian noise; acoustic noise; acoustic signal processing; automobiles; hidden Markov models; speech recognition; -10 dB; Gaussian noise; HMM; SNR; TIDIGITS database; artificially added car noise; car noise environments; database; noise compensation algorithm; parallel model combination concept; performance; recognition accuracy; speech recognition; speech recognition systems; Additive noise; Cepstral analysis; Databases; Gaussian noise; Hidden Markov models; Signal to noise ratio; Speech enhancement; Speech recognition; Testing; Working environment noise;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on
Conference_Location :
Detroit, MI
Print_ISBN :
0-7803-2431-5
DOI :
10.1109/ICASSP.1995.479621
