DSpace Repository

Acoustic Modeling for Spoken Dialogue Systems Based on Unsupervised Utterance-based Selective Training

Show simple item record

dc.contributor.author Cincarek, Tobias en
dc.contributor.author Toda, Tomoki en
dc.contributor.author Saruwatari, Hiroshi en
dc.contributor.author Shikano, Kiyohiro en
dc.date.accessioned 2012-08-22T07:58:54Z en
dc.date.available 2012-08-22T07:58:54Z en
dc.date.issued 2006-09 en
dc.identifier.uri http://hdl.handle.net/10061/8141 en
dc.description INTERSPEECH2006: the 9th International Conference on Spoken Language Processing (ICSLP), September 17-21, 2006, Pittsburgh, Pennsylvania, USA. en
dc.description.abstract The construction of high-performance acoustic models for certain speech recognition tasks is very costly and time-consuming, since it most often requires the collection and transcription of large amounts of task-specific speech data. In this paper acoustic modeling for spoken dialogue systems based on unsupervised selective training is examined. The main idea is to select those training utterances from an (untranscribed) speech data pool, so that the likelihood of a separate small (transcribed) development speech data set is maximized. If only the selected data are employed to retrain the initial acoustic models, a better performance is achieved than when retraining with all collected data. Using the proposed approach it is also possible to considerably reduce the costs for human-labeling of the speech data without compromising the performance. Furthermore, the method provides means for automatic task-adaptation of acoustic models, e.g. to adult or children speech. This is important, since detailed information about each automatically collected utterance is usually not available. en
dc.language.iso en en
dc.rights Copyright 2006 ISCA en
dc.subject speech revognition en
dc.subject acoustic model en
dc.subject unsupervised training en
dc.subject utterance-based selection en
dc.subject spoken dialogue system en
dc.title Acoustic Modeling for Spoken Dialogue Systems Based on Unsupervised Utterance-based Selective Training en
dc.type.nii Conference Paper en
dc.textversion Publisher en
dc.identifier.spage 1722 en
dc.identifier.epage 1725 en
dc.identifier.artnum 1481 en
dc.identifier.NAIST-ID 73292716 en


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account