Unsupervised Speaker Identification in TV Broadcast Based on Written Names

Identifying speakers in TV broadcast in an unsupervised way (i.e., without biometric models) is a solution for avoiding costly annotations. Existing methods usually use pronounced names, as a source of names, for identifying speech clusters provided by a diarization step but this source is too impre...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on audio, speech, and language processing speech, and language processing, 2015-01, Vol.23 (1), p.57-68
Hauptverfasser: Poignant, Johann, Besacier, Laurent, Quénot, Georges
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Identifying speakers in TV broadcast in an unsupervised way (i.e., without biometric models) is a solution for avoiding costly annotations. Existing methods usually use pronounced names, as a source of names, for identifying speech clusters provided by a diarization step but this source is too imprecise for having sufficient confidence. To overcome this issue, another source of names can be used: the names written in a title block in the image track. We first compared these two sources of names on their abilities to provide the name of the speakers in TV broadcast. This study shows that it is more interesting to use written names for their high precision for identifying the current speaker. We also propose two approaches for finding speaker identity based only on names written in the image track. With the "late naming" approach, we propose different propagations of written names onto clusters. Our second proposition, "Early naming," modifies the speaker diarization module (agglomerative clustering) by adding constraints preventing two clusters with different associated written names to be merged together. These methods were tested on the REPERE corpus phase 1, containing 3 hours of annotated videos. Our best "late naming" system reaches an F-measure of 73.1%. "early naming" improves over this result both in terms of identification error rate and of stability of the clustering stopping criterion. By comparison, a mono-modal, supervised speaker identification system with 535 speaker models trained on matching development data and additional TV and radio data only provided a 57.2% F-measure.
ISSN:2329-9290
1558-7916
2329-9304
DOI:10.1109/TASLP.2014.2367822