Automatic speaker segmentation using multiple features and distance measures: A comparison of three approaches

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2006

Autores

Margarita Kotti (Autor) Outra; Luis Gustavo P M Martins (Autor) Outra; Emmanouil Benetos (Autor) Outra; Jaime S Cardoso (Autor) FCUP; Constantine Kotropoulos (Autor) Outra

Ata de Conferência Internacional

Título: 2006 IEEE International Conference on Multimedia and Expo - ICME 2006, Vols 1-5, Proceedings

Páginas: 1101-1104

IEEE International Conference on Multimedia and Expo (ICME 2006)

Toronto, CANADA, JUL 09-12, 2006

Indexação

ISI Web of Knowledge - 8 Citações

Scopus - 8 Citações

Classificação Científica

FOS: Ciências da engenharia e tecnologias > Engenharia electrotécnica, electrónica e informática

CORDIS: Ciências Tecnológicas > Tecnologia > Tecnologia de computadores > Processamento de voz

Outras Informações

ID Authenticus: P-004-R3J

DOI: 10.1109/icme.2006.262727

Abstract (EN): This paper addresses the problem of unsupervised speaker change detection. Three systems based on the Bayesian Information Criterion (BIC) are tested. The first system investigates the AudioSpectrumCentroid and the AudioWaveformEnvelope features, implements a dynamic thresholding followed by a fusion scheme, and finally applies BIC. The second method is a real-time one that uses a metric-based approach employing the line spectral pairs and the BIC to validate a potential speaker change point. The third method consists of three modules. In the first module, a measure based on second-order statistics is used; in the second module, the Euclidean distance and T-2 Hotelling statistic are applied; and in the third module, the BIC is utilized. The experiments are carried out on a dataset created by concatenating speakers from the TIMIT database, that is referred to as the TIMIT data set. A comparison between the performance of the three systems is made based on t-statistics.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 4