Vocal Style Factorization For Effective Speaker Recognition In Affective Scenarios

Abstract

The accuracy of automated speaker recognition is negatively impacted by change in emotions in a person's speech. In this paper, we hypothesize that speaker identity is composed of various vocal style factors that may be learned from unlabeled data and re-combined using a neural network to generate a holistic speaker identity representation for affective scenarios. In this regard, we propose the E-Vector architecture, composed of a 1-D CNN for learning speaker identity features and a vocal style factorization technique for determining vocal styles. Experiments conducted on the MSP-Podcast dataset demonstrate that the proposed architecture improves state-of-the-art speaker recognition accuracy in the affective domain over baseline ECAPA-TDNN speaker recognition models. For instance, the true match rate at a false match rate of 1% improves from 27.6% to 46.2%.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysandler2023vocal

Related papers

• Is Style All You Need? Dependencies Between Emotion And Gst-based Speaker Recognition (2022)0.00
• Disentanglement Of Emotional Style And Speaker Identity For Expressive Voice Conversion (2021)10.97
• Dual-model Prediction Of Affective Engagement And Vocal Attractiveness From Speaker Expressiveness In Video Learning (2026)0.00
• Seen And Unseen Emotional Style Transfer For Voice Conversion With A New Emotional Speech Dataset (2020)16.34
• X-vectors Meet Emotions: A Study On Dependencies Between Emotion And Speaker Recognition (2020)14.23
• Speaker And Style Disentanglement Of Speech Based On Contrastive Predictive Coding Supported Factorized Variational Autoencoder (2024)2.26
• Attention-based Conditioning Methods Using Variable Frame Rate For Style-robust Speaker Verification (2022)2.26
• Emotion Invariant Speaker Embeddings For Speaker Identification With Emotional Speech (2020)0.00