This paper discusses the problem of learning language from unprocessed text and speech signals, concentrating on the problem of learning a lexicon. In particular, it argues for a ...
Written documents created through dictation differ significantly from a true verbatim transcript of the recorded speech. This poses an obstacle in automatic dictation systems as s...
Maximilian Bisani, Paul Vozila, Olivier Divay, Jef...
Two experiments investigated the mechanism by which listeners adjust their interpretation of accented speech that is similar to a regional dialect of American English. Only a subs...
Jessica Maye, Richard N. Aslin, Michael K. Tanenha...
The high availability of video streams is making necessary mechanisms for indexing such contents in the Web world. In this paper we focus on news programs and we propose a mechani...
For TV and radio shows containing narrowband speech, Speech-to-text (STT) accuracy on the narrowband audio can be improved by using an acoustic model trained on acoustically match...