Plenary Lecture
Speech Assessment based on Entropy and Similarity Measures
Professor Michele Della Ventura
Music Academy 'Studio Musica'
Treviso, ITALY.
E-mail: michele.dellaventura@tin.it
Abstract: Identifying similarities between audio signals is an important goal for the Speech Recognition Systems. In this paper, a new method for the assessment of the similarity between two audio signals is proposed. Based on the entropy theory, the audio signals are segmented and compared on the basis of the information value carried by each segment: this value is obtained considering an alphabet derived from the trend lines of each audio signal. This is an empirical methodology that provides results expressed in numbers that may be analysed by means of an isometric diagram accommodates a better interpretation of the results.
Brief Biography of the Speaker: Michele Della Ventura, professor of Music Technology, is a learning expert, researcher and instructional designer. His research interests include correlation between music and mathematics with a particular emphasis on artificial intelligence research in the field of computer-aided analysis of tonal music; intelligent systems; enhancing teaching and learning with technology; assessment for learning and strategies and models for the effective integration of technology into the curriculum at all academic levels. He is the author of several articles presented at many conferences and published in international science magazines and high school textbooks (also featured at the International Book Salon of Turin in 2012 and 2018). He proofreads articles and is a member of scientific committees in International Conferences. He has delivered numerous invited talks at international conferences and world-renowned institutes in Italy, Austria, Canada, China, Czech Republic, France, Germany, Hong Kong, Hungary, Ireland, Japan, Norway, Poland, Portugal, Romania, Singapore, Spain, UK, US (Baltimora, Boston, Las Vegas, New York, Washington). Michele Della Ventura is also consultant in Big Data and Semantic Technology projects in Italy and he leads an interdisciplinary research group in the domain of Computer-based Speech Assessment.