Harmonic Cues for Number of Simultaneous Speakers Estimation

Rafi U, Bardeli R. Harmonic Cues for Number of Simultaneous Speakers Estimation. In: AES Conference: 53rd International Conference: Semantic Audio. Audio Engineering Society; 2014. Paper P1-12. Available from: https://aes.org/publications/elibrary-page/?id=17088

@inproceedings{Rafi2014_17088,
  author = {Rafi, Umer and Bardeli, Rolf},
  title = {{Harmonic Cues for Number of Simultaneous Speakers Estimation}},
  booktitle = {AES Conference: 53rd International Conference: Semantic Audio},
  note = {Paper P1-12},
  year = {2014},
  month = jan,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=17088}
}

TY  - CPAPER
TI  - Harmonic Cues for Number of Simultaneous Speakers Estimation
AU  - Rafi, Umer
AU  - Bardeli, Rolf
T2  - AES Conference: 53rd International Conference: Semantic Audio
M1  - Paper P1-12
PY  - 2014
DA  - 2014/01/06
UR  - https://aes.org/publications/elibrary-page/?id=17088
PB  - Audio Engineering Society
LA  - en
AB  - Overlapped speech, where several speakers are speaking simultaneously, is a common occurence in multiparty discussions such as meetings. This kind of speech presents a great challenge to automatic speech processing systems such as speech recognition systems and speaker diarisation systems. In recent speaker diarisation systems, a large portion of the remaining error comes from overlapped speech. So far little work has been done on detecting overlapped speech and the number of speakers present in overlapped speech. In this paper we first describe a model-based approach for estimating the number of simultaneous speakers. Then, we propose a new approach called Spectral Peak Clustering where instead of training statistical models we extract spectral peaks from the input data and then cluster them into components by using a similarity measure between peaks where each component represents a speaker present in the input data.
ER  -