Abstract
In spite of the great success of the i-vector/PLDA framework, speaker verification in noisy environments remains a challenge. To compensate for the variability of i-vectors caused by different levels of background noise, this paper proposes a new framework, namely SNR-invariant PLDA, for robust speaker verification. By assuming that i-vectors extracted from utterances falling within a narrow SNR range share similar SNRspecific information, the paper introduces an SNR factor to the conventional PLDA model. Then, the SNR-related variability and the speaker-related variability embedded in the i-vectors are modeled by the SNR factor and the speaker factor, respectively. Accordingly, an i-vector is represented by a linear combination of three components: speaker, SNR, and channel. During verification, the variability due to SNR and channels are marginalized out when computing the marginal likelihood ratio. Experiments based on NIST 2012 SRE show that SNR-invariant PLDA achieves superior performance when compared with the conventional PLDA and SNR-dependent mixture of PLDA.
Original language | English |
---|---|
Pages (from-to) | 2317-2321 |
Number of pages | 5 |
Journal | Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH |
Volume | 2015-January |
Publication status | Published - 1 Jan 2015 |
Event | 16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015 - International Congress Center, Dresden, Germany Duration: 6 Sep 2015 → 10 Sep 2015 |
Keywords
- I-vector
- PLDA
- SNR-invariant
- Speaker verification
ASJC Scopus subject areas
- Language and Linguistics
- Human-Computer Interaction
- Signal Processing
- Software
- Modelling and Simulation