106 citations · 385 across the 23 of their papers we have counts for
3 papers · 1 filter
Real to H-space Encoder for Speech Recognition
Titouan Parcollet, Mohamed Morchid, Georges Linarès +1
Deep neural networks (DNNs) and more precisely recurrent neural networks (RNNs) are at the core of modern automatic speech recognition systems, due to their efficiency to process i…
Speech recognition with quaternion neural networks
Titouan Parcollet, Mirco Ravanelli, Mohamed Morchid +2
Neural network architectures are at the core of powerful automatic speech recognition systems (ASR). However, while recent researches focus on novel model architectures, the acoust…
Bidirectional Quaternion Long-Short Term Memory Recurrent Neural Networks for Speech Recognition
Titouan Parcollet, Mohamed Morchid, Georges Linarès +1
Recurrent neural networks (RNN) are at the core of modern automatic speech recognition (ASR) systems. In particular, long-short term memory (LSTM) recurrent neural networks have ac…