Time Frequency Principal Components: Application to Speaker Identification
dc.citation.bibtexName | inproceedings | en_US |
dc.citation.conferenceName | Proceedings of EUROSPEECH | en_US |
dc.contributor.author | Magrin-Chagnolleau, Ivan | en_US |
dc.contributor.author | Durou, Geoffrey | en_US |
dc.contributor.org | Digital Signal Processing (http://dsp.rice.edu/) | en_US |
dc.date.accessioned | 2007-10-31T00:52:23Z | |
dc.date.available | 2007-10-31T00:52:23Z | |
dc.date.issued | 1999-01-01 | en |
dc.date.modified | 2004-11-05 | en_US |
dc.date.note | 2004-01-14 | en_US |
dc.date.submitted | 1999-01-01 | en_US |
dc.description | Conference Paper | en_US |
dc.description.abstract | In this paper, we propose a formalism, called vector filtering of spectral trajectories, which allows to integrate under a common formalism a lot of speech parameterization approaches. We then propose a new filtering in this framework, called time-frequency principal components (TFPC) of speech. We apply this new filtering in the framework of speaker identification, using a subset of the POLYCOST database. The results show an improvement of roughly 20% compared to the use of the classical cepstral coefficients augmented by their Delta-coefficients. | en_US |
dc.identifier.citation | I. Magrin-Chagnolleau and G. Durou, "Time Frequency Principal Components: Application to Speaker Identification," 1999. | |
dc.identifier.uri | https://hdl.handle.net/1911/20076 | |
dc.language.iso | eng | |
dc.subject | Temporary | * |
dc.subject.keyword | Temporary | en_US |
dc.subject.other | Multifractals | en_US |
dc.title | Time Frequency Principal Components: Application to Speaker Identification | en_US |
dc.type | Conference paper | |
dc.type.dcmi | Text |
Files
Original bundle
1 - 3 of 3
No Thumbnail Available
- Name:
- Mag1999Jan5TimeFrequ.PPT
- Size:
- 94.5 KB
- Format:
- Microsoft Powerpoint