TY - JOUR
T1 - Integrating phrasing and intonation modelling using syntactic and morphosyntactic information
AU - Díaz, Francisco Campillo
AU - van Santen, Jan
AU - Banga, Eduardo Rodríguez
N1 - Funding Information:
The work reported here was carried out while the first author was a visiting post-doctoral researcher at the Center for Spoken Language Understanding, with funding from the Xunta de Galicia “Isidro Parga Pondal” research programme and PGIDIT05TIC32202-PR programme, and with support from NSF Grant 0205731, “ITR: Prosody Generation for Child Oriented Speech Synthesis” (PI Jan van Santen), and MEC under the Project TEC2006-13694-C03-03. Thanks also to Paul Hosom and Raychel Moldover, for their comments and suggestions on the paper.
PY - 2009/5
Y1 - 2009/5
N2 - This paper focuses on the relationship between intonation and syntactic and morphosyntactic information. Although intonation and syntax are both related to dependencies between the different parts of a sentence, and are therefore related to meaning, the precise influence of grammar on intonation is not clear. We describe a novel method that uses syntactic and part-of-speech features in the framework of corpus-based intonation modelling, and which integrates part of the phrasing algorithm in the unit selection stage. Subjective tests confirm an improvement in the quality of the resulting synthetic intonation: 75% of the sentences synthesised with the new intonation model were considered to be better or much better than the sentences synthesised using the old model, while only 7.5% of sentences were rated as worse or much worse.
AB - This paper focuses on the relationship between intonation and syntactic and morphosyntactic information. Although intonation and syntax are both related to dependencies between the different parts of a sentence, and are therefore related to meaning, the precise influence of grammar on intonation is not clear. We describe a novel method that uses syntactic and part-of-speech features in the framework of corpus-based intonation modelling, and which integrates part of the phrasing algorithm in the unit selection stage. Subjective tests confirm an improvement in the quality of the resulting synthetic intonation: 75% of the sentences synthesised with the new intonation model were considered to be better or much better than the sentences synthesised using the old model, while only 7.5% of sentences were rated as worse or much worse.
KW - Corpus-based
KW - Intonation modelling
KW - POS
KW - Phrasing
KW - Syntax
KW - Unit selection
UR - http://www.scopus.com/inward/record.url?scp=61749092962&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=61749092962&partnerID=8YFLogxK
U2 - 10.1016/j.specom.2009.01.007
DO - 10.1016/j.specom.2009.01.007
M3 - Article
AN - SCOPUS:61749092962
SN - 0167-6393
VL - 51
SP - 452
EP - 465
JO - Speech Communication
JF - Speech Communication
IS - 5
ER -