😮‍💨

Speech & Audio

Created
2026/03/08 15:06
Tags
Paper Reviews
Paper Title
Authors
Date
Venue
Field
Rating
Review Status
Review Date
Key Findings
URL
DuplexCascade: Full-Duplex Speech-to-Speech Dialogue with VAD-Free Cascaded ASR–LLM–TTS Pipeline and Micro-Turn Optimization
Open
0
Full-duplex
4 - Good
Todo
2026/03/31 06:20
https://arxiv.org/pdf/2603.09180
SCALING SPEECH TOKENIZERS WITH DIFFUSION AUTOENCODERS
Open
0
Todo
2026/03/18 16:43
Qwen3-Omni
Open
0
Todo
2026/03/18 16:40
PersonaPlex
Open
0
Todo
2026/03/18 16:39
Moshi: a speech-text foundation model for real-time dialogue
Open
Kyutai
2024
Full-duplex
SpeechLLM
Audio Codec
5 - Excellent
In Progress
2026/04/03 09:32
https://arxiv.org/pdf/2410.00037
Qwen3-TTS
Open
Alibaba
2026
Audio Codec
TTS
SpeechLLM
4 - Good
Todo
2026/04/03 09:08
VibeVoice
Open
0
Todo
2026/03/11 10:20
VoxCPM
Open
0
Todo
2026/03/11 10:20
MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows
Open
Xiquan Li
2025
Flow Matching
Diffusion Acceleration
4 - Good
Todo
2026/03/11 07:23
https://arxiv.org/pdf/2508.06098
speech test
Open
0
Todo
2026/03/09 02:34