Picture for Junichi Yamagishi

Junichi Yamagishi

Libri2Vox Dataset: Target Speaker Extraction with Diverse Speaker Conditions and Synthetic Data

Add code
Dec 17, 2024
Viaarxiv icon

It Takes Two: Real-time Co-Speech Two-person's Interaction Generation via Reactive Auto-regressive Diffusion Model

Add code
Dec 03, 2024
Viaarxiv icon

The First VoicePrivacy Attacker Challenge Evaluation Plan

Add code
Oct 09, 2024
Figure 1 for The First VoicePrivacy Attacker Challenge Evaluation Plan
Figure 2 for The First VoicePrivacy Attacker Challenge Evaluation Plan
Figure 3 for The First VoicePrivacy Attacker Challenge Evaluation Plan
Figure 4 for The First VoicePrivacy Attacker Challenge Evaluation Plan
Viaarxiv icon

AfriHuBERT: A self-supervised speech representation model for African languages

Add code
Sep 30, 2024
Viaarxiv icon

The VoiceMOS Challenge 2024: Beyond Speech Quality Prediction

Add code
Sep 11, 2024
Viaarxiv icon

Spoofing-Aware Speaker Verification Robust Against Domain and Channel Mismatches

Add code
Sep 10, 2024
Viaarxiv icon

Disentangling the Prosody and Semantic Information with Pre-trained Model for In-Context Learning based Zero-Shot Voice Conversion

Add code
Sep 10, 2024
Viaarxiv icon

A Preliminary Case Study on Long-Form In-the-Wild Audio Spoofing Detection

Add code
Aug 26, 2024
Viaarxiv icon

ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale

Add code
Aug 16, 2024
Viaarxiv icon

The VoicePrivacy 2022 Challenge: Progress and Perspectives in Voice Anonymisation

Add code
Jul 16, 2024
Figure 1 for The VoicePrivacy 2022 Challenge: Progress and Perspectives in Voice Anonymisation
Figure 2 for The VoicePrivacy 2022 Challenge: Progress and Perspectives in Voice Anonymisation
Figure 3 for The VoicePrivacy 2022 Challenge: Progress and Perspectives in Voice Anonymisation
Figure 4 for The VoicePrivacy 2022 Challenge: Progress and Perspectives in Voice Anonymisation
Viaarxiv icon