-
Can automatic speech transcripts be used for large scale TV stream descriptio...
International audience -
vAssist : the virtual interactive assistant for daily home-care
The "Ambient Assisted Living" program supports the vAssist project for the European community. The portable devices (smartphones) are the keys to integrate open-source... -
Continuous space models with neural networks in natural language processing
The purpose of language models is in general to capture and to model regularities of language, thereby capturing morphological, syntactical and distributional... -
Statistical methods in multi-speaker automatic speech recognition
International audience -
Statistical methods in multi-speaker automatic speech recognition
International audience -
Attelage de systèmes de transcription automatique de la parole
This thesis presents work in the area of Large Vocabulary ContinuousSpeech Recognition (LVCSR) system combination. The thesis focuses onmethods for harnessing... -
Incorporating Named Entity Recognition into the Speech Transcription Process
International audience -
Hands-free speech-sound interactions at home
International audience -
Ad-hoc language models for automatic speech recognition
The three pillars of an automatic speech recognition system are the lexicon, the languagemodel and the acoustic model. The lexicon provides all the words that can... -
Improvement of Multi-Band Speech Recognition
Colloque avec actes et comité de lecture. -
Dealing With Loss of Synchronism in Multi-Band Continuous Speech Recognition ...
Contribution à un ouvrage. -
Dealing with distant relationships in natural language modelling for automati...
Colloque avec actes et comité de lecture. internationale. -
Transformation of Jacobian matrices for noisy speech recognition
Colloque avec actes et comité de lecture. internationale. -
Fast Channel and Noise Compensation in the Spectral Domain
Colloque avec actes et comité de lecture. internationale.
