Incorporating prosody into neural speech processing pipelines: applications on automatic speech transcription and spoken language machine translation

In this dissertation, I study the inclusion of prosody into two applications that involve speech understanding:~automatic speech transcription and spoken language translation. In the former case, I propose a method that uses an attention mechanism over parallel sequences of prosodic and morphosyntac...

Descripción completa

Detalles Bibliográficos
Autor: Öktem, Alp
Tipo de recurso: tesis doctoral
Estado:Versión publicada
Fecha de publicación:2019
País:España
Institución:CBUC, CESCA
Repositorio:TDR. Tesis Doctorales en Red
OAI Identifier:oai:www.tdx.cat:10803/666222
Acceso en línea:http://hdl.handle.net/10803/666222
Access Level:acceso abierto
Palabra clave:Prosody
Automatic speech transcription
Punctuation restoration
Spoken language machine translation
Bilingual spoken corpus
Prosòdia
Transcripció automàtica de la parla
Restauració de la puntuació
Traducció automàtica de llenguatge oral
Corpus bilingües
62
Descripción
Sumario:In this dissertation, I study the inclusion of prosody into two applications that involve speech understanding:~automatic speech transcription and spoken language translation. In the former case, I propose a method that uses an attention mechanism over parallel sequences of prosodic and morphosyntactic features. Results indicate an $F_1$ score of 70.3\% in terms of overall punctuation generation accuracy. In the latter problem I deal with enhancing spoken language translation with prosody. A neural machine translation system trained with movie-domain data is adapted with pause features using a prosodically annotated bilingual dataset. Results show that prosodic punctuation generation as a preliminary step to translation increases translation accuracy by 1\% in terms of BLEU scores. Encoding pauses as an extra encoding feature gives an additional 1\% increase to this number. The system is further extended to jointly predict pause features in order to be used as an input to a text-to-speech system.