Real to H-space Encoder for Speech Recognition

Abstract : 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 input sequences. Recently, it has been shown that different input representations, based on multidimensional algebras, such as complex and quaternion numbers, are able to bring to neural networks a more natural, compressive and powerful representation of the input signal by outperforming common real-valued NNs. Indeed, quaternion-valued neural networks (QNNs) better learn both internal dependencies, such as the relation between the Mel-filter-bank value of a specific time frame and its time derivatives, and global dependencies, describing the relations that exist between time frames. Nonetheless, QNNs are limited to quaternion-valued input signals, and it is difficult to benefit from this powerful representation with real-valued input data. This paper proposes to tackle this weakness by introducing a real-to-quaternion encoder that allows QNNs to process any one dimensional input features, such as traditional Mel-filter-banks for automatic speech recognition.
Document type :
Conference papers
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02158201
Contributor : Titouan Parcollet <>
Submitted on : Monday, June 17, 2019 - 10:15:39 PM
Last modification on : Thursday, June 20, 2019 - 1:33:00 AM

File

INTERSPEECH_2019___Projection_...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02158201, version 1

Collections

Citation

Titouan Parcollet, Mohamed Morchid, Georges Linarès, Renato de Mori. Real to H-space Encoder for Speech Recognition. INTERSPEECH 2019, Jun 2019, Graz, Austria. ⟨hal-02158201⟩

Share

Metrics

Record views

7

Files downloads

4