Ιδρυματικό Αποθετήριο [SANDBOX]
Πολυτεχνείο Κρήτης
EN  |  EL

Αναζήτηση

Πλοήγηση

Ο Χώρος μου

Linear dynamical models in speech synthesis

Tsiaras Vasileios, Ranniery Maia, Diakoloukas Vasilis, Stylianou, Yannis, Digalakis Vasilis

Απλή Εγγραφή


URIhttp://purl.tuc.gr/dl/dias/42E91AFE-C479-4B0E-9797-C9300FB9FF56-
Αναγνωριστικόhttps://doi.org/10.1109/ICASSP.2014.6853606-
Αναγνωριστικόhttp://ieeexplore.ieee.org/document/6853606/-
Γλώσσαen-
ΤίτλοςLinear dynamical models in speech synthesisen
ΔημιουργόςTsiaras Vasileiosen
ΔημιουργόςΤσιαρας Βασιλειοςel
ΔημιουργόςRanniery Maiaen
ΔημιουργόςDiakoloukas Vasilisen
ΔημιουργόςΔιακολουκας Βασιλeioςel
ΔημιουργόςStylianou, Yannisen
ΔημιουργόςDigalakis Vasilisen
ΔημιουργόςΔιγαλακης Βασιληςel
ΕκδότηςInstitute of Electrical and Electronics Engineersen
ΠερίληψηHidden Markov models (HMMs) are becoming the dominant approach for text-to-speech synthesis (TTS). HMMs provide an attractive acoustic modeling scheme which has been exhaustively investigated and developed for many years. Modern HMM-based speech synthesizers have approached the quality of the best state-of-the-art unit selection systems. However, we believe that statistical parametric speech synthesis has not reached its potential, since HMMs are limited by several assumptions which do not apply to the properties of speech. We, therefore, propose in this paper to use Lin-ear Dynamical Models (LDMs) instead of HMMs. LDMs can better model the dynamics of speech and can produce a naturally smoother trajectory of the synthesized speech. We perform a series of experiments using different system configurations to check on the performance of LDMs for speech synthesis. We show that LDM-based synthesizers can outperform HMM-based ones in terms of cepstral distance and are a very promising acoustic modeling alternative for statistical parametric TTS. en
ΤύποςΠλήρης Δημοσίευση σε Συνέδριοel
ΤύποςConference Full Paperen
Άδεια Χρήσηςhttp://creativecommons.org/licenses/by/4.0/en
Ημερομηνία2015-11-08-
Ημερομηνία Δημοσίευσης2014-
Θεματική ΚατηγορίαHMMs (Hidden Markov models)en
Θεματική Κατηγορίαhidden markov modelsen
Θεματική Κατηγορίαhmms hidden markov modelsen
Βιβλιογραφική ΑναφοράV. Tsiaras, R. Maia, V. Diakoloukas, Y. Stylianou and V. Digalakis, "Linear dynamical models in speech synthesis", in 2014 IEEE Int. Conf. on Acoust., Speech and Sign. Process. (ICASSP) doi: 10.1109/ICASSP.2014.6853606en

Υπηρεσίες

Στατιστικά