Mostra el registre d'ítem simple
Multiple multilabeling to improve HMM-based speech recognition in noise
dc.contributor.author | Hernando Pericás, Francisco Javier |
dc.contributor.author | Mariño Acebal, José Bernardo |
dc.contributor.author | Nadeu Camprubí, Climent |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions |
dc.date.accessioned | 2016-07-13T07:34:23Z |
dc.date.available | 2016-07-13T07:34:23Z |
dc.date.issued | 1993 |
dc.identifier.citation | Hernando, J., Mariño, J.B., Nadeu, C. Multiple multilabeling to improve HMM-based speech recognition in noise. A: European Conference on Speech Communication and Technology. "EUROSPEECH '93: 3rd European Conference on Speech Communication and Technology: Berlin, Germany: 21-23 September 1993". Berlin: 1993, p. 1643-1646. |
dc.identifier.uri | http://hdl.handle.net/2117/88719 |
dc.description.abstract | The performance of existing speech recognition systems degrades rapidly in the presence of background noise when training and testing cannot be done under the same ambient conditions. The aim of this paper is to propose the application of a simple multilabeling method, instead of the standard vector quantization -so called labeling-, as the front end for a speech recognizer based on the Vector Quantization (VQ) and Hidden Markov Models (HMM) approaches in order to increase its robustness to noise. Furthermore, not only cepstrum but also other features such as energy and dynamic parameters are evaluated and quantized independently in the multilabeling stage to represent more accurately characteristics of speech. The result of this process is a multiple multilabeling. Experimental results in the presence of additive white noise and car environment clearly demonstrate its good performance in isolated word recognition in noisy environments. |
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 | Markov processes |
dc.subject.other | Noisy speech recognition |
dc.subject.other | Vector quantization |
dc.subject.other | Hidden Markov models |
dc.title | Multiple multilabeling to improve HMM-based speech recognition in noise |
dc.type | Conference report |
dc.subject.lemac | Processament de la parla |
dc.subject.lemac | Markov, Processos de |
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 | 18768954 |
dc.description.version | Postprint (published version) |
local.citation.author | Hernando, J.; Mariño, J.B.; Nadeu, C. |
local.citation.contributor | European Conference on Speech Communication and Technology |
local.citation.pubplace | Berlin |
local.citation.publicationName | EUROSPEECH '93: 3rd European Conference on Speech Communication and Technology: Berlin, Germany: 21-23 September 1993 |
local.citation.startingPage | 1643 |
local.citation.endingPage | 1646 |