Skip to Main content Skip to Navigation
Journal articles

Real to H-space Autoencoders for Theme Identification in Telephone Conversations

Abstract : Machine learning (ML) and deep learning with deep neural networks (DNN), have drastically improved the performances of modern systems on numerous spoken language understanding (SLU) related tasks. Since most of current researches focus on new neural architectures to enhance the performances in realistic conditions, few recent works investigated the use of different algebras with neural networks (NN), to better represent the nature of the data being processed. To this extent, quaternion-valued neural networks (QNN) have shown better performances, and an important reduction of the number of neural parameters compared to traditional real-valued neural networks, when dealing with multidimensional signal. Nonetheless, the use of QNNs is strictly limited to quaternion input or output features. This paper introduces a new unsupervised method based on a hybrid autoencoder (AE) called real-to-quaternion autoencoder (R2H), to extract a quaternion-valued input signal from any real-valued data, to be processed by QNNs. The experiments performed to identify the most related theme of a given telephone conversation from a customer care service (CCS), demonstrate that the R2H approach outperforms all the previously established models, either real-or quaternion-valued ones, in term of accuracy and with up to four times fewer neural parameters.
Document type :
Journal articles
Complete list of metadatas

Cited literature [63 references]  Display  Hide  Download
Contributor : Titouan Parcollet <>
Submitted on : Tuesday, December 10, 2019 - 11:56:06 AM
Last modification on : Thursday, June 18, 2020 - 12:58:24 PM
Long-term archiving on: : Wednesday, March 11, 2020 - 10:22:26 PM


Files produced by the author(s)




Titouan Parcollet, Mohamed Morchid, Xavier Bost, Georges Linarès, Renato de Mori. Real to H-space Autoencoders for Theme Identification in Telephone Conversations. IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2020, 28, pp.198-210. ⟨10.1109/TASLP.2019.2950596⟩. ⟨hal-02402005⟩



Record views


Files downloads