Wang, B; Liakata, M; Ni, H; Lyons, T; Nevado-Holgado, AJ; Saunders, K; (2019) A Path Signature Approach for Speech Emotion Recognition. In: Proceedings Interspeech 2019. (pp. pp. 1661-1665). ISCA: Graz, Austria.

Preview

Text aPathSignature4SpeechRecogntion.pdf - Published Version Download (294kB) | Preview

Abstract

Automatic speech emotion recognition (SER) remains a difficult task within human-computer interaction, despite increasing interest in the research community. One key challenge is how to effectively integrate short-term characterisation of speech segments with long-term information such as temporal variations. Motivated by the numerical approximation theory of stochastic differential equations (SDEs), we propose the novel use of path signatures. The latter provide a pathwise definition to solve SDEs, for the integration of short speech frames. Furthermore we propose a hierarchical tree structure of path signatures, to capture both global and local information. A simple tree-based convolutional neural network (TBCNN) is used for learning the structural information stemming from dyadic path-tree signatures. Our experimental results on a widely used benchmark dataset demonstrate comparable performance to complex neural network based systems.

Download activity - last month

Export as XMLCSVJSON

Download activity - last 12 months

Export as JSONCSVXML

Downloads by country - last 12 months

Export as CSVXMLJSON

Archive Staff Only

View Item