Speaker Change Detection with Privacy-Preserving Audio Cues
| Type of publication: | Idiap-RR |
| Citation: | Parthasarathi_Idiap-RR-23-2009 |
| Number: | Idiap-RR-23-2009 |
| Year: | 2009 |
| Month: | 8 |
| Institution: | Idiap |
| Address: | Idiap Research Institute, Martigny, Switzerland |
| Abstract: | In this paper we investigate a set of privacy-sensitive audio features for speaker change detection (SCD) in multiparty conversations. These features are based on three different principles: characterizing the excitation source information using linear prediction residual, characterizing subband spectral information shown to contain speaker information, and characterizing the general shape of the spectrum. Experiments show that the performance of the privacy-sensitive features is comparable or better than that of the state-of-the-art full-band spectral-based features, namely, mel frequency cepstral coefficients, which suggests that socially acceptable ways of recording conversations in real-life is feasible. |
| Keywords: | |
| Projects |
Idiap SNSF-MULTI IM2 |
| Authors | |
| Crossref by |
Parthasarathi_ICMI-MLMI2009_2009 |
| Added by: | [ADM] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
