Application of the pairwise variability index of speech rhythm with particle swarm optimization to the classification of native and non-native accents. (March 2018)

• Record Type: Journal Article
• Authors: Gharsellaoui, Soumaya; Selouani, Sid Ahmed; Cichocki, Wladyslaw; Alotaibi, Yousef; Dahmane, Adel Omar
• Is Part Of: Computer speech & language. Volume 48(2018)
• Page Start: 67
• Page End: 79
• Publication Date: 2018-03
• Subjects: Speech rhythm -- Rhythm metrics -- Pairwise variability index -- Classification -- Modern standard Arabic -- Particle swarm optimization -- Non-native accent; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2017.10.006
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: A new rhythm metric, Optimized Pairwise Variability Index (O-PVI), is proposed. The O-PVI provides a generalization of conventional PVI rhythm metrics. Particle Swarm Optimization (PSO) is used to select the best O-PVI parameters. The combined PSO/O-PVI approach achieves best classification of Arabic native/non-native speakers. Experiments compare interval- and PVI-based rhythm metrics. Abstract: This paper presents a technique that applies the pairwise variability index (PVI), a rhythm metric that quantifies variability in speech rhythm, to the classification of speech varieties. The technique combines the Particle Swarm Optimization (PSO) algorithm with a generalization of several rhythm metrics that are based on the PVI. The performance of this optimization-oriented classification is compared with classification that uses conventional (both PVI-based and interval-based) rhythm metrics. Application is made to the classification of native and non-native Arabic speech using data are from the West Point Arabic Speech Corpus; experiments are based on segmental durations and use Support Vector Machine (SVM) classification. Results show that the optimization-oriented classification provides a better discrimination between native and non-native speech varieties than classification based of the conventional rhythm metrics. When added to different combinations of these conventional metrics, the optimization-oriented procedure consistently improves classification rates.