 |
Conference papers
Combining transcription-based and acoustic-based speaker identifications for broadcast news
Abstract : In this paper, we consider the issue of speaker identification within audio records of broadcast news. The speaker identity information is extracted from both transcript-based and acoustic-based speaker identification systems. This information is combined in the belief functions framework, which makes coherent the knowledge representation of the problem. The Kuhn-Munkres algorithm is used to optimize the assignment problem of speaker identities and speaker clusters. Experiments carried out on French broadcast news from the French evaluation campaign ESTER show the efficiency of the proposed combination method.
Cited literature [12 references]
https://hal.archives-ouvertes.fr/hal-01433486
Contributor : Sylvain Meignier <>
Submitted on : Monday, April 3, 2017 - 9:57:26 PM
Last modification on : Tuesday, December 8, 2020 - 9:44:20 AM
Long-term archiving on: : Tuesday, July 4, 2017 - 2:50:28 PM
Contributor : Sylvain Meignier <>
Submitted on : Monday, April 3, 2017 - 9:57:26 PM
Last modification on : Tuesday, December 8, 2020 - 9:44:20 AM
Long-term archiving on: : Tuesday, July 4, 2017 - 2:50:28 PM
File
Khoury_ICASSP_2012.pdf
Files produced by the author(s)