Loading...
conference paper
LP-TRAP: Linear predictive temporal patterns
2004
International Conference on Spoken Language Processing (ICSLP)
Autoregressive modeling is applied for approximating the temporal evolution of spectral density in critical-band-sized sub-bands of a segment of speech signal. The generalized autocorrelation linear predictive technique allows for a compromise between fitting the peaks and the troughs of the Hilbert envelope of the signal in the sub-band. The cosine transform coefficients of the approximated sub-band envelopes, computed recursively from the all-pole polynomials, are used as inputs to a TRAP-based speech recognition system and are shown to improve recognition accuracy.
Loading...
Name
rr04-59.pdf
Access type
openaccess
Size
315.45 KB
Format
Adobe PDF
Checksum (MD5)
39437f99162ec80a9903381343a16b52