Neural networks are a useful alternative to Gaussian mixture models for acoustic modeling; however, training multilayer networks involves a difficult, nonconvex optimization that...
This paper presents a semantic confidence measure that aims to predict the relevance of automatic transcripts for a task of Spoken Document Retrieval (SDR). The proposed predicti...
Syntactic analysis of search queries is important for a variety of information-retrieval tasks; however, the lack of annotated data makes training query analysis models difficult...
Kuzman Ganchev, Keith Hall, Ryan T. McDonald, Slav...
There is considerable interest in interdisciplinary combinations of automatic speech recognition (ASR), machine learning, natural language processing, text classification and info...
Mark Dredze, Aren Jansen, Glen Coppersmith, Ken Wa...
available in the Conference Program). 2007: (with E. Jarmołowicz, Z. Malisz i M. Szczyszek) Gesture, Prosody and Lexicon in ented Dialogues: Progress Report. (Poznań Linguistic M...