Mostrar el registro sencillo del ítem

dc.creatorCoto Jiménez, Marvin
dc.creatorGoddard Close, John
dc.date.accessioned2022-03-25T20:06:21Z
dc.date.available2022-03-25T20:06:21Z
dc.date.issued2016
dc.identifier.citationhttps://link.springer.com/chapter/10.1007/978-3-319-39393-3_28es_ES
dc.identifier.isbn978-3-319-39393-3
dc.identifier.urihttps://hdl.handle.net/10669/86292
dc.descriptionPart of the Lecture Notes in Computer Science book series (LNCS, volume 9703).es_ES
dc.description.abstractRecent developments in speech synthesis have produced systems capable of providing intelligible speech, and researchers now strive to create models that more accurately mimic human voices. One such development is the incorporation of multiple linguistic styles in various languages and accents. HMM-based speech synthesis is of great interest to researchers, due to its ability to produce sophisticated features with a small footprint. Despite such progress, its quality has not yet reached the level of the current predominant unit-selection approaches, that select and concatenate recordings of real speech. Recent efforts have been made in the direction of improving HMM-based systems. In this paper, we present the application of long short-term memory deep neural networks as a postfiltering step in HMM-based speech synthesis. Our motivation stems from a desire to obtain spectral characteristics closer to those of natural speech. The results described in the paper indicate that HMM-voices can be improved using this approach.es_ES
dc.description.sponsorshipUniversidad de Costa Rica/[]/UCR/Costa Ricaes_ES
dc.description.sponsorshipConsejo Nacional de Ciencia y Tecnología/[CB-2012-01, No.182432]/CONACyT/Méxicoes_ES
dc.language.isoenges_ES
dc.sourcePattern Recognition (pp.280-289).Guanajuato, Mexico: Springer, Chames_ES
dc.subjectLong short-term memory (LSTM)es_ES
dc.subjectHidden Markov Models (HMM)es_ES
dc.subjectSpeech synthesises_ES
dc.subjectStatistical parametric speech synthesises_ES
dc.subjectPostfilteringes_ES
dc.subjectDeep learninges_ES
dc.titleLSTM deep neural networks postfiltering for improving the quality of synthetic voiceses_ES
dc.typecomunicación de congresoes_ES
dc.identifier.doi10.1007/978-3-319-39393-3_28
dc.description.procedenceUCR::Vicerrectoría de Docencia::Ingeniería::Facultad de Ingeniería::Escuela de Ingeniería Eléctricaes_ES


Ficheros en el ítem

Thumbnail

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem