Voiceextender: Short-utterance Text-independent Speaker Verification With Guided Diffusion Model

Abstract

Speaker verification (SV) performance deteriorates as utterances become shorter. To this end, we propose a new architecture called VoiceExtender which provides a promising solution for improving SV performance when handling short-duration speech signals. We use two guided diffusion models, the built-in and the external speaker embedding (SE) guided diffusion model, both of which utilize a diffusion model-based sample generator that leverages SE guidance to augment the speech features based on a short utterance. Extensive experimental results on the VoxCeleb1 dataset show that our method outperforms the baseline, with relative improvements in equal error rate (EER) of 46.1%, 35.7%, 10.4%, and 5.7% for the short utterance conditions of 0.5, 1.0, 1.5, and 2.0 seconds, respectively.

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keyhe2023voiceextender

Related papers

• Diff-sv: A Unified Hierarchical Framework For Noise-robust Speaker Verification Using Score-based Diffusion Probabilistic Models (2023)6.34
• Extract And Diffuse: Latent Integration For Improved Diffusion-based Speech And Vocal Enhancement (2024)0.00
• Variance-preserving-based Interpolation Diffusion Models For Speech Enhancement (2023)0.00
• Self-supervised Learning With Diffusion-based Multichannel Speech Enhancement For Speaker Verification Under Noisy Conditions (2023)0.00
• Diffv2s: Diffusion-based Video-to-speech Synthesis With Vision-guided Speaker Embedding (2023)8.82
• Seeing Through The Conversation: Audio-visual Speech Separation Based On Diffusion Model (2023)7.50
• Eres2netv2: Boosting Short-duration Speaker Verification Performance With Computational Efficiency (2024)9.41
• A Variance-preserving Interpolation Approach For Diffusion Models With Applications To Single Channel Speech Enhancement And Recognition (2024)8.82