I-vector Transformation Using Conditional Generative Adversarial Networks For Short Utterance Speaker Verification

Abstract

I-vector based text-independent speaker verification (SV) systems often have poor performance with short utterances, as the biased phonetic distribution in a short utterance makes the extracted i-vector unreliable. This paper proposes an i-vector compensation method using a generative adversarial network (GAN), where its generator network is trained to generate a compensated i-vector from a short-utterance i-vector and its discriminator network is trained to determine whether an i-vector is generated by the generator or the one extracted from a long utterance. Additionally, we assign two other learning tasks to the GAN to stabilize its training and to make the generated ivector more speaker-specific. Speaker verification experiments on the NIST SRE 2008 "10sec-10sec" condition show that our method reduced the equal error rate by 11.3% from the conventional i-vector and PLDA system.

Stats

• citations12
• S2 citations—
• github stars0
• HF likes0
• heat score8.35
• arxiv keyzhang2018i

Related papers

• Generative X-vectors For Text-independent Speaker Verification (2018)7.16
• Discriminatively Re-trained I-vector Extractor For Speaker Recognition (2018)5.84
• Deep Neural Network Based I-vector Mapping For Speaker Verification Using Short Utterances (2018)0.00
• Generative Adversarial Speaker Embedding Networks For Domain Robust End-to-end Speaker Verification (2018)0.00
• Factorization Of Discriminatively Trained I-vector Extractor For Speaker Recognition (2019)0.00
• Investigation Of Using VAE For I-vector Speaker Verification (2017)0.00
• Quality Measures For Speaker Verification With Short Utterances (2019)0.00
• End-to-end DNN Based Speaker Recognition Inspired By I-vector And PLDA (2017)10.35