Mostra el registre d'ítem simple
Using x-gram for efficient speech recognition
dc.contributor.author | Bonafonte Cávez, Antonio |
dc.contributor.author | Mariño Acebal, José Bernardo |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions |
dc.date.accessioned | 2017-07-27T08:50:55Z |
dc.date.available | 2017-07-27T08:50:55Z |
dc.date.issued | 1998 |
dc.identifier.citation | Bonafonte, A., Mariño, J.B. Using x-gram for efficient speech recognition. A: International Conference on Spoken Language Processing. "ICSLP 1998: International Conference on Spoken Language Processing: Sydney, Australia: November 30-December 4, 1998". Sidney: Robert H. Mannel and Jordi Robert-Ribes, 1998, p. 2559-2562. |
dc.identifier.isbn | 1 876346 17 5 |
dc.identifier.uri | http://hdl.handle.net/2117/106909 |
dc.description.abstract | X-grams are a generalization of the n-grams, where the number of previous conditioning words is different for each case and decided from the training data. X-grams reduce perplexity with respect to trigrams and need less number of parameters. In this paper, the representation of the x-grams using finite state automata is considered. This representation leads to a new model, the non-deterministic x-grams, an approximation that is much more efficient, suffering small degradation on the modeling capability. Empirical experiments for a continuous speech recognition task show how, for each ending word, the number of transitions is reduced from 1222 (the size of the lexicon) to around 66. |
dc.format.extent | 4 p. |
dc.language.iso | eng |
dc.publisher | Robert H. Mannel and Jordi Robert-Ribes |
dc.rights | Attribution-NonCommercial-NoDerivs 3.0 Spain |
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.lcsh | Telecommunication |
dc.title | Using x-gram for efficient speech recognition |
dc.type | Conference report |
dc.subject.lemac | Telecomunicació |
dc.contributor.group | Universitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla |
dc.description.peerreviewed | Peer Reviewed |
dc.relation.publisherversion | http://www.isca-speech.org/archive/icslp_1998/index.html |
dc.rights.access | Open Access |
local.identifier.drac | 2453305 |
dc.description.version | Postprint (published version) |
local.citation.author | Bonafonte, A.; Mariño, J.B. |
local.citation.contributor | International Conference on Spoken Language Processing |
local.citation.pubplace | Sidney |
local.citation.publicationName | ICSLP 1998: International Conference on Spoken Language Processing: Sydney, Australia: November 30-December 4, 1998 |
local.citation.startingPage | 2559 |
local.citation.endingPage | 2562 |