Abstract— Especially for tasks like automatic meeting transcription, it would be useful to automatically recognize speech also while multiple speakers are talking simultaneously....
Dorothea Kolossa, Shoko Araki, Marc Delcroix, Tomo...
Spoken Document Retrieval (SDR) is a promising technology for enhancing the utility of spoken materials. After the spoken documents have been transcribed by using a Large Vocabula...
Despite the ready availability of digital recording technology and the continually decreasing cost of digital storage, browsing audio recordings remains a tedious task. This paper...
Sunil Vemuri, Philip DeCamp, Walter Bender, Chris ...
Over the years, the focus in noise robust speech recognition has shifted from noise robust features to model based techniques such as parallel model combination and uncertainty de...
Kris Demuynck, Xueru Zhang, Dirk Van Compernolle, ...
We propose a novelapproach to automaticallygrowing and pruning Hierarchical Mixtures of Experts. The constructive algorithm proposed here enables large hierarchies consisting of s...