An Open-source State-of-the-art Toolbox for Broadcast News Diarization

被引:0
作者
Rouvier, Mickael [1 ]
Dupuy, Gregor [1 ]
Gay, Paul [1 ]
Khoury, Elie [1 ]
Merlin, Teva [1 ]
Meignier, Sylvain [1 ]
机构
[1] LUNAM Univ, LIUM, Le Mans, France
来源
14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5 | 2013年
关键词
speaker diarization; broadcast news; open-source; SPEAKER DIARIZATION;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper presents the LIUM open-source speaker diarization toolbox, mostly dedicated to broadcast news. This tool includes both Hierarchical Agglomerative Clustering using well-known measures such as BIC and CLR, and the new ILP clustering algorithm using i-vectors. Diarization systems are tested on the French evaluation data from ESTER, ETAPE and REPERE campaigns.
引用
收藏
页码:1476 / 1480
页数:5
相关论文
共 31 条
[1]  
[Anonymous], LREC 8 INT C LANG RE
[2]  
[Anonymous], P 6 INT 9 EUR C SPEE
[3]  
[Anonymous], 2004, Fall 2004 rich transcription (rt-04f) evaluation plan
[4]  
[Anonymous], THESIS
[5]  
[Anonymous], DARPA SPEECH REC WOR
[6]   Multistage speaker diarization of broadcast news [J].
Barras, Claude ;
Zhu, Xuan ;
Meignier, Sylvain ;
Gauvain, Jean-Luc .
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2006, 14 (05) :1505-1512
[7]  
Ben M., 2004, P INT C SPOK LANG PR
[8]  
Bonastre J.-F., 2008, OD SPEAK LANG REC WO
[9]  
Bousquet P.-M., 2011, P INT FLOR IT
[10]   Front-End Factor Analysis for Speaker Verification [J].
Dehak, Najim ;
Kenny, Patrick J. ;
Dehak, Reda ;
Dumouchel, Pierre ;
Ouellet, Pierre .
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2011, 19 (04) :788-798