Speech Recognition with Quaternion Neural Networks

Abstract : Neural network architectures are at the core of powerful automatic speech recognition systems (ASR). However, while recent researches focus on novel model architectures, the acoustic input features remain almost unchanged. Traditional ASR systems rely on multidimensional acoustic features such as the Mel filter bank energies alongside with the first, and second order derivatives to characterize time-frames that compose the signal sequence. Considering that these components describe three different views of the same element, neural networks have to learn both the internal relations that exist within these features, and external or global dependencies that exist between the time-frames. Quaternion-valued neural networks (QNN), recently received an important interest from researchers to process and learn such relations in multidimensional spaces. Indeed, quaternion numbers and QNNs have shown their efficiency to process multidimensional inputs as entities, to encode internal dependencies, and to solve many tasks with up to four times less learning parameters than real-valued models. We propose to investigate modern quaternion-valued models such as convolutional and recurrent quaternion neural networks in the context of speech recognition with the TIMIT dataset. The experiments show that QNNs always outperform real-valued equivalent models with way less free parameters, leading to a more efficient, compact, and expressive representation of the relevant information.
Document type :
Conference papers
Complete list of metadatas

Cited literature [40 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02107651
Contributor : Titouan Parcollet <>
Submitted on : Tuesday, April 23, 2019 - 5:43:45 PM
Last modification on : Saturday, May 4, 2019 - 1:24:46 AM

File

1811.09678.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02107651, version 1
  • ARXIV : 1811.09678

Collections

Citation

Titouan Parcollet, Mirco Ravanelli, Mohamed Morchid, Georges Linares, Renato de Mori. Speech Recognition with Quaternion Neural Networks. NIPS 2018 - IRASL Workshop, Dec 2018, Montréal, Canada. ⟨hal-02107651⟩

Share

Metrics

Record views

10

Files downloads

23