INTERSPEECH 2012
13th Annual Conference of the International Speech Communication Association

Portland, OR, USA
September 9-13, 2012

Towards an Unsupervised Speaking Style Voice Building Framework: Multi.Style Speaker Diarization

Jaime Lorenzo-Trueba (1), Beatriz Martinez-Gonzalez (1), Veronica Lopez–Ludeña (1), Roberto Barra-Chicote (1), Javier Ferreiros (1), Junichi Yamagishi (2), Juan M. Montero (1)

(1) Speech Technology Group, ETSIT, Universidad Politecnica de Madrid, Spain
(2) Centre for Speech Technology Research, University of Edinburgh, UK

Current text.to.speech systems are developed using studio-recorded speech in a neutral style or based on acted emotions. However, the proliferation of media sharing sites would allow developing a new generation of speech.based systems which could cope with spontaneous and styled speech. This paper proposes an architecture to deal with realistic recordings and carries out some experiments on unsupervised speaker diarization. In order to maximize the speaker purity of the clusters while keeping a high speaker coverage, the paper evaluates the F-measure of a diarization module, achieving high scores (>85%) especially when the clusters are longer than 30 seconds, even for the more spontaneous and expressive styles (such as talk shows or sports).

Index Terms: expressive speech synthesis, speaker diarization, speaking styles, voice cloning.

Full Paper

Bibliographic reference.  Lorenzo-Trueba, Jaime / Martinez-Gonzalez, Beatriz / Lopez–Ludeña, Veronica / Barra-Chicote, Roberto / Ferreiros, Javier / Yamagishi, Junichi / Montero, Juan M. (2012): "Towards an unsupervised speaking style voice building framework: multi.style speaker diarization", In INTERSPEECH-2012, 2278-2281.