Debating Truth: Debate-driven Claim Verification with Multiple Large Language Model Agents
Paper • 2507.19090 • Published
AI & ML interests
Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.
Recent Activity
View all activity
HarryHe
authored 2
papers about 23 hours ago
HarryHe
submitted a
paper to Daily Papers 7 days ago
RMSnow
authored 15
papers 16 days ago
Qwen-Music Technical Report
Paper • 2607.11699 • Published • 30
Closing the Modality Reasoning Gap for Speech Large Language Models
Paper • 2601.05543 • Published • 1
SpeechJudge: Towards Human-Level Judgment for Speech Naturalness
Paper • 2511.07931 • Published
The Singing Voice Conversion Challenge 2025: From Singer Identity Conversion To Singing Style Conversion
Paper • 2509.15629 • Published
AnyAccomp: Generalizable Accompaniment Generation via Quantized Melodic Bottleneck
Paper • 2509.14052 • Published • 1
Advancing Zero-shot Text-to-Speech Intelligibility across Diverse Domains via Preference Alignment
Paper • 2505.04113 • Published
Vevo2: Bridging Controllable Speech and Singing Voice Generation via Unified Prosody Learning
Paper • 2508.16332 • Published
TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling
Paper • 2508.16790 • Published • 10
From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring
Paper • 2506.09996 • Published • 2
Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement
Paper • 2502.07243 • Published • 1
Metis: A Foundation Speech Generation Model with Masked Generative Pre-training
Paper • 2502.03128 • Published • 2
Overview of the Amphion Toolkit (v0.2)
Paper • 2501.15442 • Published • 4
MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer
Paper • 2409.00750 • Published • 6
SingVisio: Visual Analytics of Diffusion Model for Singing Voice Conversion
Paper • 2402.12660 • Published
Leveraging Content-based Features from Multiple Acoustic Models for Singing Voice Conversion
Paper • 2310.11160 • Published
jiaqili3
submitted a
paper to Daily Papers about 1 month ago
Source and computation of w2vbert2_mean_var_stats_emilia.pt
4
#4 opened about 2 months ago
by 
Vartul27