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

Rajarajeswari, P; Beg, OA

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.

Citation

Rajarajeswari, P., & Beg, O. (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), 2150055. https://doi.org/10.1142/S021951942150055X

• Journal Article Type: Article
• Acceptance Date: Jul 13, 2021
• Online Publication Date: Sep 8, 2021
• Publication Date: Sep 8, 2021
• Deposit Date: Jul 14, 2021
• Publicly Available Date: Sep 8, 2022
• Journal: Journal of Mechanics in Medicine and Biology
• Print ISSN: 0219-5194
• Electronic ISSN: 1793-6810
• Publisher: World Scientific Publishing
• Volume: 21
• Issue: 07
• Pages: 2150055
• DOI: https://doi.org/10.1142/S021951942150055X
• Publisher URL: https://doi.org/10.1142/S021951942150055X
• Related Public URLs: http://www.worldscientific.com/worldscinet/jmmb
• Additional Information: 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