PLP$^2$: Autoregressive modeling of auditory-like 2-D spectro-temporal patterns
Type of publication: | Idiap-RR |
Citation: | marios-rr-04-60 |
Number: | Idiap-RR-60-2004 |
Year: | 2004 |
Institution: | IDIAP |
Note: | Accepted for publication in the Workshop on Statistical and Perceptual Audio Processing (SAPA) 2004 |
Abstract: | The temporal trajectories of the spectral energy in auditory critical bands over 250~ms segments are approximated by an all-pole model, the time-domain dual of conventional linear prediction. This quarter-second auditory spectro-temporal pattern is further smoothed by iterative alternation of spectral and temporal all-pole modeling. Just as Perceptual Linear Prediction (PLP) uses an autoregressive model in the frequency domain to estimate peaks in an auditory-like short-term spectral slice, PLP$^2$ uses all-pole modeling in both time and frequency domains to estimate peaks of a two-dimensional spectro-temporal pattern, motivated by considerations of the auditory system. |
Userfields: | ipdmembership={speech}, |
Keywords: | |
Projects |
Idiap |
Authors | |
Crossref by |
marios-rr-04-60b |
Added by: | [UNK] |
Total mark: | 0 |
Attachments
|
|
Notes
|
|
|