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

• Published in: IEEE/ACM transactions on audio, speech, and language processing Vol. 28; pp. 198 - 210
• Main Authors: Parcollet, Titouan, Morchid, Mohamed, Bost, Xavier, Linares, Georges, De Mori, Renato
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); Institute of Electrical and Electronics Engineers
• Subjects: Artificial neural networks; Computer Science; Customer services; Feature extraction; Features extraction; Machine learning; Neural networks; Parameters; Performance enhancement; quaternion autoencoder; quaternion neural networks; Quaternions; Semantics; Signal processing; Speech recognition; spoken language understanding; Task analysis; Telephone sets; Voice recognition; Index Terms-Features extraction; spoken language understanding; quaternion autoencoder; quaternion neural networks
• ISSN: 2329-9290; 2329-9304
• DOI: 10.1109/TASLP.2019.2950596

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 article 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.