Mostra el registre d'ítem simple
On the decorrelation of filter-bank energies in speech recognition
dc.contributor.author | Nadeu Camprubí, Climent |
dc.contributor.author | Hernando Pericás, Francisco Javier |
dc.contributor.author | Gorricho Moreno, Monica |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions |
dc.date.accessioned | 2016-07-13T08:48:35Z |
dc.date.available | 2016-07-13T08:48:35Z |
dc.date.issued | 1995 |
dc.identifier.citation | Nadeu, C., Hernando, J., Gorricho, M. On the decorrelation of filter-bank energies in speech recognition. A: European Conference on Speech Communication and Technology. "EUROSPEECH '95: 4th European Conference on Speech Communication and Technology: Madrid, Spain: 18-21 September 1995". Madrid: 1995, p. 1381-1384. |
dc.identifier.isbn | 1018-4074 |
dc.identifier.uri | http://hdl.handle.net/2117/88731 |
dc.description.abstract | Cepstral coefficients are widely used in speech recognition. In this paper, we claim that they are not the best way of representing the spectral envelope, at least for some usual speech recognition systems. In fact, cepstrum has several disadvantages: poor physical meaning, need of transformation, and low capacity of adaptation to some recognition systems. In this paper, we propose a new representation that significantly outperforms both mel-cepstrum and LPC-cepstrum techniques in both recognition rate and computational cost. It consists of filtering the frequency sequence of filter-bank energies with an extremely simple filter that equalizes the variance of the cepstral coefficients. Excellent results of the new technique using a continuous observation density HMM recognition system and two very different recognition tasks, connected digits and phone recognition, are presented. |
dc.format.extent | 4 p. |
dc.language.iso | eng |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ |
dc.subject | Àrees temàtiques de la UPC::Enginyeria de la telecomunicació |
dc.subject | Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la parla i del senyal acústic |
dc.subject.lcsh | Speech processing systems |
dc.subject.lcsh | Filters and filtration |
dc.subject.other | Speech recognition |
dc.subject.other | Filter-bank energy |
dc.subject.other | Cepstral coefficient |
dc.subject.other | Low capacity |
dc.title | On the decorrelation of filter-bank energies in speech recognition |
dc.type | Conference report |
dc.subject.lemac | Processament de la parla |
dc.subject.lemac | Filtres i filtració |
dc.contributor.group | Universitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla |
dc.description.peerreviewed | Peer Reviewed |
dc.rights.access | Open Access |
local.identifier.drac | 2448315 |
dc.description.version | Postprint (published version) |
local.citation.author | Nadeu, C.; Hernando, J.; Gorricho, M. |
local.citation.contributor | European Conference on Speech Communication and Technology |
local.citation.pubplace | Madrid |
local.citation.publicationName | EUROSPEECH '95: 4th European Conference on Speech Communication and Technology: Madrid, Spain: 18-21 September 1995 |
local.citation.startingPage | 1381 |
local.citation.endingPage | 1384 |