Abstract
The i-vector representation and probabilistic linear discriminant analysis (PLDA) have shown state-of-the-art performance in many speaker verification systems. However, in real-world environments, additive and convolutive noise cause mismatches between training and recognition conditions, degrading the performance. In this paper, a fusion system that combines a multi-condition PLDA model and a mixture of SNR-dependent PLDA models is proposed to make the verification system noise robust. The SNR of test utterances is used to determine the best SNR-dependent PLDA model to score against the target-speaker's i-vectors. The performance of the fusion system is demonstrated on NIST 2012 SRE. Results show that the SNR-dependent PLDA models can reduce EER and that the fusion system is more robust than the conventional i-vector/PLDA systems under noisy conditions. It is also found that the SNR-dependent PLDA models are insensitive to Z-norm parameters.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 9th International Symposium on Chinese Spoken Language Processing, ISCSLP 2014 |
| Publisher | IEEE |
| Pages | 619-623 |
| Number of pages | 5 |
| ISBN (Electronic) | 9781479942206 |
| DOIs | |
| Publication status | Published - 24 Oct 2014 |
| Event | 9th International Symposium on Chinese Spoken Language Processing, ISCSLP 2014 - Singapore, Singapore Duration: 12 Sept 2014 → 14 Sept 2014 |
Conference
| Conference | 9th International Symposium on Chinese Spoken Language Processing, ISCSLP 2014 |
|---|---|
| Country/Territory | Singapore |
| City | Singapore |
| Period | 12/09/14 → 14/09/14 |
Keywords
- i-vectors
- LDA
- NIST 2012 SRE
- noise robustness
- probabilistic
- Speaker verification
ASJC Scopus subject areas
- Information Systems
- Computer Science Applications
- Software