Clustering Expressive Speech Styles in Audiobooks Using Glottal Source Parameters.
2011 (English)In: 12th Annual Conference of the International-Speech-Communication-Association 2011 (INTERSPEECH 2011), ISCA-INT SPEECH COMMUNICATION ASSOC , 2011, 2409-2412 p.Conference paper (Refereed)Text
A great challenge for text-to-speech synthesis is to produce ex- pressive speech. The main problem is that it is difficult to syn- thesise high-quality speech using expressive corpora. With the increasing interest in audiobook corpora for speech synthesis, there is a demand to synthesise speech which is rich in prosody, emotions and voice styles. In this work, Self-Organising Fea- ture Maps (SOFM) are used for clustering the speech data using voice quality parameters of the glottal source, in order to map out the variety of voice styles in the corpus. Subjective evalu- ation showed that this clustering method successfully separated the speech data into groups of utterances associated with dif- ferent voice characteristics. This work can be applied in unit- selection synthesis by selecting appropriate data sets to synthe- sise utterances with specific voice styles. It can also be used in parametric speech synthesis to model different voice styles separately.
Place, publisher, year, edition, pages
ISCA-INT SPEECH COMMUNICATION ASSOC , 2011. 2409-2412 p.
Engineering and Technology
IdentifiersURN: urn:nbn:se:kth:diva-185519ISI: 000316502201094ScopusID: 2-s2.0-84865709194ISBN: 978-1-61839-270-1OAI: oai:DiVA.org:kth-185519DiVA: diva2:922790
12th Annual Conference of the International-Speech-Communication-Association 2011 (INTERSPEECH 2011) AUG 27-31
QC 201604262016-04-252016-04-212016-04-26Bibliographically approved