16th Annual Conference of the International Speech Communication Association

Dresden, Germany
September 6-10, 2015

SNR-Invariant PLDA Modeling for Robust Speaker Verification

Na Li, Man-Wai Mak

Hong Kong Polytechnic University, China

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 SNR-specific 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.

Full Paper

Bibliographic reference.  Li, Na / Mak, Man-Wai (2015): "SNR-invariant PLDA modeling for robust speaker verification", In INTERSPEECH-2015, 2317-2321.