Abstract
Recently we have investigated the use of state-of-the-art textindependent and text-dependent speaker verification algorithms for a text-dependent user authentication task and obtained satisfactory results mainly by using a fair amount of text-dependent development data. In our study, best results were obtained using the NAP framework rather than using the more advanced JFA and i-vector-based frameworks. In this work we investigate the ability to build high accuracy i-vectorbased systems by leveraging widely available conversational data. We explore various techniques for transforming conversational sessions in such a way that attributes which are more relevant to the text-dependent task are enhanced. Using these techniques we managed to reduce verification error significantly.
| Original language | English |
|---|---|
| Pages (from-to) | 2470-2473 |
| Number of pages | 4 |
| Journal | Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH |
| State | Published - 2013 |
| Externally published | Yes |
| Event | 14th Annual Conference of the International Speech Communication Association, INTERSPEECH 2013 - Lyon, France Duration: 25 Aug 2013 → 29 Aug 2013 |
Keywords
- Speaker verification
- Text-dependent
- Transfer learning