Toward Fail-Safe Speaker Recognition: Trial-Based Calibration with a Reject Option
The output scores of most of the speaker recognition systems are not directly interpretable as stand-alone values. For this reason, a calibration step is usually performed on the scores to convert them into proper likelihood ratios, which have a clear probabilistic interpretation. The standard calib...
Guardado en:
| Publicado: |
2019
|
|---|---|
| Materias: | |
| Acceso en línea: | https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_23299290_v27_n1_p140_Ferrer http://hdl.handle.net/20.500.12110/paper_23299290_v27_n1_p140_Ferrer |
| Aporte de: |
Ejemplares similares
-
Toward Fail-Safe Speaker Recognition: Trial-Based Calibration with a Reject Option
por: Ferrer, L., et al. -
Improving robustness of speaker recognition to new conditions using unlabeled data
por: Castan, D., et al. -
Improving robustness of speaker recognition to new conditions using unlabeled data
Publicado: (2017) -
On the issue of calibration in DNN-based speaker recognition systems
por: McLaren, M., et al. -
On the issue of calibration in DNN-based speaker recognition systems
Publicado: (2016)