We propose a novel multi-stream framework for continuous conversational speech recognition which employs bidirectional Long Short-Term Memory (BLSTM) networks for phoneme predicti...
With the purpose of improving Spoken Language Understanding (SLU) performance, a combination of different acoustic speech recognition (ASR) systems is proposed. State a-posteriori...
Abstract. This paper presents the final version of the Czech Broadcast Conversation Corpus released at the Linguistic Data Consortium (LDC). The corpus contains 72 recordings of a...
Many works on speech processing have dealt with auto-regressive (AR) models for spectral envelope and formant frequency estimation, mostly focusing on the estimation of the AR par...
Contending with signal variability due to source and channel effects is a critical problem in automatic emotion recognition. Any approach in mitigating these effects however has t...
Carlos Busso, Angeliki Metallinou, Shrikanth S. Na...