Vo-Ve: An Explainable Voice-Vector for Speaker Identity Evaluation

2025/06/24 by Jae Jun Lee, Lee, Jaejun, Kyogu Lee +1
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #Speech Recognition and Synthesis #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2506.19446

openalex publication_date 2025/06/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper, we propose Vo-Ve, a novel voice-vector embedding that captures speaker identity. Unlike conventional speaker embeddings, Vo-Ve is explainable, as it contains the probabilities of explicit voice attribute classes. Through extensive analysis, we demonstrate that Vo-Ve not only evaluates speaker similarity competitively with conventional techniques but also provides an interpretable explanation in terms of voice attributes. We strongly believe that Vo-Ve can enhance evaluation schemes across various speech tasks due to its high-level explainability.

Citations

• Improvement Speaker Similarity for Zero-Shot Any-to-Any Voice Conversion of Whispered and Regular Speech
• Hear Your Face: Face-based voice conversion with F0 estimation
• LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning
• Noise-Robust Voice Conversion by Conditional Denoising Training Using Latent Variables of Recording Quality and Environment
• PromptSpeaker: Speaker Generation Based on Text Descriptions
• PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-to-Speech Using Natural Language Descriptions
• PromptTTS 2: Describing and Generating Voices with Text Prompt
• Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale
• LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus
• Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
• Robust Speech Recognition via Large-Scale Weak Supervision
• PromptTTS: Controllable Text-to-Speech with Text Descriptions
• Content-Dependent Fine-Grained Speaker Embedding for Zero-Shot Speaker Adaptation in Text-to-Speech Synthesis
• WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
• LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech
• LRS3-TED: a large-scale dataset for visual speech recognition
• Generalized End-to-End Loss for Speaker Verification

Related

• Explainable Attribute-Based Speaker Verification
• Analyzing and Improving Speaker Similarity Assessment for Speech Synthesis
• ExPO: Explainable Phonetic Trait-Oriented Network for Speaker Verification
• What Does the Speaker Embedding Encode?
• Estimating Uniqueness of I-Vector Representation of Human Voice