Hidden Markov Models (HMMs) provide a simple and effective framework for modelling time-varying spectral vector sequences. As a consequence, almost all present day large vocabula...
Accessing specific or salient parts of multimedia recordings remains a challenge as there is no obvious way of structuring and representing a mix of space-based and timebased med...
Spoken utterance retrieval was largely studied in the last decades, with the purpose of indexing large audio databases or of detecting keywords in continuous speech streams. While...
Mickael Rouvier, Georges Linares, Benjamin Lecoute...
Phonetic decision trees are a key concept in acoustic modeling for large vocabulary continuous speech recognition. Although discriminative training has become a major line of rese...
SUITEKeys is a speech user interface for motor-disabled computer users. This interface provides access to all available functionality of a computer by modeling interaction at the ...