An active learning method for speaker identity annotation in audio recordings

Pierre-Alexandre Broux (1) , David Doukhan (1) , Simon Petitrenaud (2) , Sylvain Meignier (2) , Jean Carrive (1)

1 INA - Institut National de l'Audiovisuel
2 LIUM - Laboratoire d'Informatique de l'Université du Mans

Given that manual annotation of speech is an expensive and long process, we attempt in this paper to assist an anno-tator to perform a speaker diarization. This assistance takes place in an annotation background for a large amount of archives. We propose a method which decreases the intervention number of a human. This method corrects a diarization by taking into account the human interventions. The experiment is done using French broadcast TV shows drawn from ANR-REPERE evaluation campaign. Our method is mainly evaluated in terms of KSR (Keystroke Saving Rate), and we reduce the number of actions needed to correct a speaker diarization output by 6.8% in absolute value.

Domaines: Informatique et langage [cs.CL]

Pierre-Alexandre Broux, David Doukhan, Simon Petitrenaud, Sylvain Meignier, Jean Carrive. An active learning method for speaker identity annotation in audio recordings. 1st International Workshop on Multimodal Media Data Analytics (MMDA 2016), Aug 2016, La Haye, Netherlands. ⟨hal-01451532⟩