Work

Evolutive HMM for multi-speaker tracking system

Year: 2002

Type: conference-paper

Abstract: Seeking within a speech sequence the speaker utterances is one of the main tasks of indexing. In this paper, the proposed speaker tracking system is defined in the case where all speaker identities are known beforehand. The conversation is modeled as an evolutive HMM-like model, in which speaker models computed are added one by one. A temporary indexing is proposed after each speaker adding and then challenged at the next step. This process is iterated until all the speakers are detected. The system has been assessed using multi-speaker messages generated by concatenation of Switchboard mono-speaker segments. The obtained results show the potentiality of the proposed solution.

Source: IEEE International Conference on Acoustics Speech and Signal Processing

DOI: 10.1109/icassp.2000.859181

Authors: S. Meignier, J.-F. Bonastre, C. Fredouille, T. Merlin

Institutions: Université d'Avignon et des Pays de Vaucluse, Laboratoire Informatique d'Avignon

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W1920021574

FWCI: 1.46

Cites: 4

Cited by: 25

Related to: 10