eprintid: 20409
rev_number: 15
eprint_status: archive
userid: 1903
dir: disk0/00/02/04/09
datestamp: 2013-10-05 08:38:23
lastmod: 2016-04-21 23:12:24
status_changed: 2013-10-05 08:38:23
type: conference_item
metadata_visibility: show
item_issues_count: 0
creators_name: Lorenzo Trueba, Jaime
creators_name: Barra Chicote, Roberto
creators_name: Raitio, Tuomo
creators_name: Obin, Nicolas
creators_name: Alku, Paavo
creators_name: Yamagishi, J.
creators_name: Montero Martínez, Juan Manuel
creators_id: jaime.lorenzo@die.upm.es
creators_id: barra@die.upm.es
title: Towards glottal source controllability in expressive speech synthesis
ispublished: pub
subjects: telecomunicaciones
keywords: Expressive speech synthesis, speaking style, glottal source modeling.
abstract: In order to obtain more human like sounding humanmachine interfaces we must first be able to give them expressive capabilities in the way of emotional and stylistic features so as to closely adequate them to the intended task. If we want to replicate those features it is not enough to merely replicate the prosodic information of fundamental frequency and speaking rhythm. The proposed additional layer is the modification of the glottal model, for which we make use of the GlottHMM parameters. This paper analyzes the viability of such an approach by verifying that the expressive nuances are captured by the aforementioned features, obtaining 95% recognition rates on styled speaking and 82% on emotional speech. Then we evaluate the effect of speaker bias and recording environment on the source modeling in order to quantify possible problems when analyzing multi-speaker databases. Finally we propose a speaking styles separation for Spanish based on prosodic features and check its perceptual significance.
date: 2012
date_type: published
full_text_status: public
pres_type: paper
pagerange: 1-4
pages: 4
event_title: InterSpeech 2012 - 13th Annual Conference of the International Speech Communication Association
event_location: Portland, Oregon
event_dates: 09/09/2012 - 13/09/2012
event_type: conference
institution: Telecomunicacion
department: Ingenieria_Electronica
refereed: TRUE
book_title: InterSpeech 2012 - 13th Annual Conference of the International Speech Communication Association
rights: by-nc-nd
citation:    Lorenzo Trueba, Jaime, Barra Chicote, Roberto, Raitio, Tuomo, Obin, Nicolas, Alku, Paavo, Yamagishi, J. and Montero Martínez, Juan Manuel  (2012).  Towards glottal source controllability in expressive speech synthesis.  In: "InterSpeech 2012 - 13th Annual Conference of the International Speech Communication Association", 09/09/2012 - 13/09/2012, Portland, Oregon. pp. 1-4.    
document_url: https://oa.upm.es/20409/1/INVE_MEM_2012_134451.pdf