One of the difficult problems of acoustic modeling for Automatic Speech Recognition (ASR) is how to adequately model the wide variety of acoustic conditions which may be present i...
This paper presents a new approach to feature analysis in automatic speech recognition (ASR) based on locality preserving projections (LPP). LPP is a manifold based dimensionality...
This paper explores the problem of identifying sentence boundaries in the transcriptions produced by automatic speech recognition systems. An experiment which determines the level...
Large vocabulary speech recognition systems fail to recognize words beyond their vocabulary, many of which are information rich terms, like named entities or foreign words. Hybrid...
Carolina Parada, Mark Dredze, Abhinav Sethy, Ariya...
We define the task of incremental or 0lag utterance segmentation, that is, the task of segmenting an ongoing speech recognition stream into utterance units, and present first resu...