Accessing Information in Spoken Audio

April 19-20, 1999
Cambridge, UK

Phonetic Transcriptions on Phrase-Level

Roeland J. F. Ordelman (1), Arjan J. van Hessen (1), and David A. van Leeuwen (2)

(1) University of Twente, Enschede, The Netherlands
(2) TNO - Human Factors Research Institute, Soesterberg, The Netherlands

Whereas nowadays within-word co-articulation effects are usually sufficiently dealt with in automatic speech recognition, this is not always the case with phrase level co-articulation effects (PLC). This paper describes a first approach in dealing with phrase level co-articulation by applying these rules on the reference transcripts used for training our recogniser and by adding a set of temporary PLC phones that later on will be mapped on the original phones. In fact we temporarily break down acoustic context into a general and a PLC context. With this method, more robust models could be trained because phones that are confused due to PLC effects like for example /v/-/f/ and /z/-/s/, receive their own models. A first attempt to apply this method is described.

Full Paper (PDF)   Full Paper (Zipped Postscript)

Bibliographic reference.  Ordelman, Roeland J. F. / Hessen, Arjan J. van / Leeuwen, David A. van (1999): "Phonetic Transcriptions on Phrase-Level", In Access-Audio-1999, 64-68.