Texto completo
Vista Previa |
PDF (Portable Document Format)
- Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (227kB) | Vista Previa |
A comparison of open-source segmentation architectures for dealing with imperfect data from the media in speech synthesis
Cita
Gallardo Antolín, Ascensión, Montero Martínez, Juan Manuel 
ORCID: https://orcid.org/0000-0002-7908-5400 and King, Simon
(2014).
A comparison of open-source segmentation architectures for dealing with imperfect data from the media in speech synthesis.
En: "15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014)", 14/09/2014 - 18/09/2014, Singapore. pp. 2370-2374.
ORCID: https://orcid.org/0000-0002-7908-5400 and King, Simon
(2014).
A comparison of open-source segmentation architectures for dealing with imperfect data from the media in speech synthesis.
En: "15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014)", 14/09/2014 - 18/09/2014, Singapore. pp. 2370-2374.
Descripción
| Título: | A comparison of open-source segmentation architectures for dealing with imperfect data from the media in speech synthesis |
|---|---|
| Autor/es: |
|
| Tipo de Documento: | Ponencia en Congreso o Jornada (Artículo) |
| Título del Evento: | 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014) |
| Fechas del Evento: | 14/09/2014 - 18/09/2014 |
| Lugar del Evento: | Singapore |
| Título del Libro: | Proceedings 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014) |
| Fecha: | 2014 |
| Materias: | |
| ODS: | |
| Palabras Clave Informales: | Diarization, audio segmentation, expressive textto-speech, media recordings |
| Escuela: | E.T.S.I. Telecomunicación (UPM) |
| Departamento: | Ingeniería Electrónica |
| Licencias Creative Commons: | Reconocimiento - Sin obra derivada - No comercial |
Resumen
Traditional Text-To-Speech (TTS) systems have been developed using especially-designed non-expressive scripted recordings. In order to develop a new generation of expressive TTS systems in the Simple4All project, real recordings from the media should be used for training new voices with a whole new range of speaking styles. However, for processing this more spontaneous material, the new systems must be able to deal with imperfect data (multi-speaker recordings, background and foreground music and noise), filtering out low-quality audio segments and creating mono-speaker clusters. In this paper we compare several architectures for combining speaker diarization and music and noise detection which improve the precision and overall quality of the segmentation.
Proyectos asociados
Tipo
Código
Acrónimo
Responsable
Título
FP7
287678
SIMPLE4ALL
University of Edinburgh
Speech synthesis that improves through adaptive learning
Más información
| ID de Registro: | 37500 |
|---|---|
| Identificador DC: | https://oa.upm.es/37500/ |
| Identificador OAI: | oai:oa.upm.es:37500 |
| Depositado por: | Memoria Investigacion |
| Depositado el: | 15 Sep 2015 18:25 |
| Ultima Modificación: | 06 Jun 2016 18:25 |
Acciones
- Estadísticas
- Exportar cita
- Editar (sólo personal del Archivo)
