An Intelligent System for Spoken Term Detection That Uses Belief Combination

Abstract

Spoken Term Detection (STD) can be considered as a sub-part of the automatic speech recognition which aims to extract the partial information from speech signals in the form of query utterances. A variety of STD techniques available in the literature employ a single source of evidence for the query utterance match/mismatch determination. In this manuscript, we develop an acoustic signal processing based approach for STD that incorporates a number of techniques for silence removal, dynamic noise filtration, and evidence combination using Dempster-Shafer Theory (DST). A "spectral-temporal features based voiced segment detection" and "energy and zero cross rate based unvoiced segment detection" are built to remove the silence segments in the speech signal. Comprehensive experiments have been performed on large speech datasets and consequently satisfactory results have been achieved with the proposed approach. Our approach improves the existing speaker dependent STD approaches, specifically the reliability of query utterance spotting by combining the evidences from multiple belief sources.Keywords: Spoken term detection, Acoustic keyword spotting, Query-by-example, Dempster-Shafer"s theory, Speech recognition, Speech processing. Acknowledgement:A special gratitude we give to Prof. Daniel Neagu, University of Bradford, whose contribution in stimulating suggestions helped us to coordinate this research in terms of statistical analysis, and performance evaluation methods.

Application of Artificial Intelligence and Wireless Networks to Music Teaching

“…In the class, teachers can use the reading point of the intelligent system to play the piece of music they need to learn and sing. The story related to the song can be intuitively demonstrated through Flash animation to enhance students' emotions when they singing the song [21,22]. Teachers can play the piano to accompany students when students sing songs and encourage students to innovate freely according to the accompaniments, which is conducive to improving the intimacy between teachers and students.…”

IoT-Enabled Flood Severity Prediction via Ensemble Machine Learning Models

“…The sensory data is collected from the Environment Agency [50], that contains a collection of datasets from various cities around the world. Each sample of the flood sensor datasets contains 11 features deemed important for predicting the severity (as illustrated in Table 2).…”

Phishing Attacks and Websites Classification Using Machine Learning and Multiple Datasets (A Comparative Analysis)

“…Phishing websites detection is a crucial step towards countering online fraud. Recent technological advancements have been made with the use of ML and data science methods in diverse application domains including aerospace [28], speech processing [29], healthcare technologies [30,32], border security [31], object recognition [33], cybercrime detection [27], smart city [35] and so on. Likewise, there have been many technological developments in the domain of cyber security specifically to automatically detect the phishing attacks, but there is still a room for a lots of improvements in this regard.…”