Now showing items 1-2 of 2
Phone recognition for spoken web search
(MediaEval Workshop, Pisa, Italy, 2011)
Aiming at both speaker independence and robustness with respect to recognition errors in the spoken queries, we have implemented a two-pass system for spoken web search. In the first pass, unconstrained phone recognition ...
Efficient harvesting of Internet audio for resource-scarce ASR
(Interspeech 2011, 2011)
Spoken recordings that have been transcribed for human reading (e.g. as captions for audiovisual material, or to provide alternative modes of access to recordings) are widely available in many languages. Such recordings ...