Skip to Main content Skip to Navigation
Conference papers

Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition

Abstract : Recently, the connectionist temporal classification (CTC) model coupled with recurrent (RNN) or convolutional neural networks (CNN), made it easier to train speech recognition systems in an end-to-end fashion. However in real-valued models , time frame components such as mel-filter-bank energies and the cepstral coefficients obtained from them, together with their first and second order derivatives, are processed as individual elements, while a natural alternative is to process such components as composed entities. We propose to group such elements in the form of quaternions and to process these quaternions using the established quaternion algebra. Quaternion numbers and quaternion neural networks have shown their efficiency to process multidimensional inputs as entities, to encode internal dependencies , and to solve many tasks with less learning parameters than real-valued models. This paper proposes to integrate multiple feature views in quaternion-valued convolutional neu-ral network (QCNN), to be used for sequence-to-sequence mapping with the CTC model. Promising results are reported using simple QCNNs in phoneme recognition experiments with the TIMIT corpus. More precisely, QCNNs obtain a lower phoneme error rate (PER) with less learning parameters than a competing model based on real-valued CNNs.
Document type :
Conference papers
Complete list of metadata

Cited literature [38 references]  Display  Hide  Download
Contributor : Titouan Parcollet <>
Submitted on : Tuesday, April 23, 2019 - 5:07:49 PM
Last modification on : Wednesday, October 14, 2020 - 4:16:38 AM


Files produced by the author(s)




Titouan Parcollet, Ying Zhang, Mohamed Morchid, Chiheb Trabelsi, Georges Linarès, et al.. Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition. Interspeech 2018, Sep 2018, HYDERABAD, India. pp.22-26, ⟨10.21437/Interspeech.2018-1898⟩. ⟨hal-02107611⟩



Record views


Files downloads