Foreign accent classification using source generator based prosodic features

Source Generator Based Prosodic Features John H.L. Hansen and Levent M. Arslan Robust Speech Processing Laboratory Duke University Department of Electrical Engineering Box 90291, Durham, North Carolina 27708-0291 ABSTRACT Speaker accent is an important issue in the formulation of robust speaker independent recognition systems. Knowledge gained from a reliable accent classi cation approach could improve overall recognition performance. In this paper, a new algorithm is proposed for foreign accent classi cation of American English. A series of experimental studies are considered which focus on establishing how speech production is varied to convey accent. The proposed method uses a source generator framework, recently proposed for analysis and recognition of speech under stress[5]. An accent sensitive database is established using speakers of American English with foreign language accents. An initial version of the classi cation algorithm classi ed speaker accent from among four di erent accents with an accuracy of 81.5% in the case of unknown text, and 88.9% assuming known text. Finally, it is shown that as accent sensitive word count increases, the ability to correctly classify accent also increases, achieving an overall classi cation rate of 92% among four accent classes. 1