1. Real to H-space Encoder for Speech Recognition
- Author
-
Georges Linarès, Mohamed Morchid, Renato De Mori, Titouan Parcollet, Laboratoire Informatique d'Avignon (LIA), Avignon Université (AU)-Centre d'Enseignement et de Recherche en Informatique - CERI, McGill University = Université McGill [Montréal, Canada], and Parcollet, Titouan
- Subjects
[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI] ,FOS: Computer and information sciences ,Sound (cs.SD) ,Relation (database) ,Computer science ,Speech recognition ,Computer Science::Neural and Evolutionary Computation ,[INFO] Computer Science [cs] ,Computer Science - Sound ,[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] ,Audio and Speech Processing (eess.AS) ,FOS: Electrical engineering, electronic engineering, information engineering ,[INFO]Computer Science [cs] ,Quaternion ,Representation (mathematics) ,Index Terms: quaternion neural networks ,Computer Science - Computation and Language ,Artificial neural network ,Frame (networking) ,Process (computing) ,speech recognition ,recurrent neural net- works ,Recurrent neural network ,Encoder ,Computation and Language (cs.CL) ,Electrical Engineering and Systems Science - Audio and Speech Processing - 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., Comment: Accepted at INTERSPEECH 2019
- Published
- 2019