Abstract / Description of output
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 he more spontaneous and expressive styles (such as talk shows or sports).
| Original language | English |
|---|---|
| Title of host publication | Proc. Interspeech 2012 |
| Subtitle of host publication | 13th Annual Conference of the International Speech Communication Association, Portland, Oregon, USA, September 9-13, 2012 |
| Publisher | ISCA |
| Publication status | Published - Sept 2012 |
Keywords / Materials (for Non-textual outputs)
- expressive speech synthesis, speaker diarization, speaking styles, voice cloning