An executable method for an intelligent speech and call recognition system using a machine learning-based approach

Rajarajeswari, P and Beg, OA ORCID: https://orcid.org/0000-0001-5925-6711 2021, 'An executable method for an intelligent speech and call recognition system using a machine learning-based approach' , Journal of Mechanics in Medicine and Biology, 21 (07) , p. 2150055.

[img] PDF - Accepted Version
Restricted to Repository staff only until 8 September 2022.

Download (584kB) | Request a copy
Access Information: Electronic version of an article published in Journal of Mechanics in Medicine and Biology, 21, 07, https://doi.org/10.1142/S021951942150055X © 2021 [copyright World Scientific Publishing Company] http://www.worldscientific.com/worldscinet/jmmb

Abstract

This paper describes a novel call recognizer system based on the machine learning approach. Current trends, intelligence, emotional recognition and other factors are important challenges in the real world. The proposed system provides robustness with high accuracy and adequate response time for human-computer interaction. Intelligence and emotion recognition from speech of human-computer interfaces are simulated via multiple classifier systems (MCS). At a higher level stage, the acoustic stream phase extracts certain acoustic features based on the pitch and energy of the signal. Here featured space is labelled with various emotional types in the training phase. Emotional categories are trained in the acoustic feature space. The semantic stream process converts speech into-text conversion in the input speech signal. Text classification algorithms are applied subsequently. The clustering and classification process is performed via a K-means algorithm. The detection of the Tone of Voice of call recognition system is achieved with the XG Boost Model for feature extraction and detection of a particular phrase in the client call phase. Speech expressions are used for understanding human emotion. The algorithms are tested and demonstrate good performance in the simulation environment.

Item Type: Article
Schools: Schools > School of Computing, Science and Engineering
Journal or Publication Title: Journal of Mechanics in Medicine and Biology
Publisher: World Scientific Publishing
ISSN: 0219-5194
Related URLs:
Depositing User: OA Beg
Date Deposited: 14 Jul 2021 13:38
Last Modified: 02 Nov 2021 09:15
URI: http://usir.salford.ac.uk/id/eprint/61215

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)

Downloads

Downloads per month over past year