In the past several years, we’ve been studying feature transformation (FT) approaches to robust automatic speech recognition (ASR) which can compensate for possible “distortio...
Large vocabulary automatic speech recognition (ASR) technologies perform well in known and controlled contexts. In less controlled conditions, however, human review is often neces...
This paper describes work within the NIST Text REtrieval Conference (TREC) over the last three years in designing and implementing evaluations of Spoken Document Retrieval (SDR) t...
John S. Garofolo, Cedric G. P. Auzanne, Ellen M. V...
Non-negative matrix factorisation (NMF) is an unsupervised learning technique that decomposes a non-negative data matrix into a product of two lower rank non-negative matrices. Th...
Alexander Bertrand, Kris Demuynck, Veronique Stout...
In missing feature based automatic speech recognition (ASR), the role of the spectro-temporal mask in providing an accurate description of the relationship between target speech a...