Show simple item record

Audio, Speech, and Language Processing, IEEE Transactions on

dc.contributor.authorWatts, O.
dc.contributor.authorYamagishi, Junichi
dc.contributor.authorKing, Simon
dc.contributor.authorBerkling, K.
dc.date.accessioned2010-12-15T14:17:07Z
dc.date.available2010-12-15T14:17:07Z
dc.date.issued2010
dc.identifier.urihttp://dx.doi.org/10.1109/TASL.2009.2035029en
dc.identifier.urihttp://hdl.handle.net/1842/4530
dc.description.abstractThe synthesis of child speech presents challenges both in the collection of data and in the building of a synthesizer from that data. We chose to build a statistical parametric synthesizer using the hidden Markov model (HMM)-based system HTS, as this technique has previously been shown to perform well for limited amounts of data, and for data collected under imperfect conditions. Six different configurations of the synthesizer were compared, using both speaker-dependent and speaker-adaptive modeling techniques, and using varying amounts of data. For comparison with HMM adaptation, techniques from voice conversion were used to transform existing synthesizers to the characteristics of the target speaker. Speaker-adaptive voices generally outperformed child speaker-dependent voices in the evaluation. HMM adaptation outperformed voice conversion style techniques when using the full target speaker corpus; with fewer adaptation data, however, no significant listener preference for either HMM adaptation or voice conversion methods was found.en
dc.publisherIEEEen
dc.titleSynthesis of Child Speech with HMM Adaptation and Voice Conversionen
dc.typeArticleen
dc.identifier.doi10.1109/TASL.2009.2035029en
rps.issue5en
rps.volume18en
rps.titleAudio, Speech, and Language Processing, IEEE Transactions onen
dc.extent.pageNumbers1005--1016en
dc.date.updated2010-12-15T14:17:07Z


Files in this item

This item appears in the following Collection(s)

Show simple item record