🤝 Open to Collab

Takuya Umeki

consome2

otoearth

·

https://www.full-duplex.ai/

AI & ML interests

Full-duplex

Recent Activity

posted an update 1 day ago

We just published our H1 2026 voice AI report through FullDuplex.ai. It covers GPT Live, the different strategies emerging in Chinese and Western voice AI, the convergence of cascade and full duplex systems, model native turn decisions, and interaction evaluation. Read it here: https://www.fullduplex.ai/reports

liked a dataset 18 days ago

ssz1111/SpokenWOZ-Test-Audio

liked a dataset 18 days ago

ssz1111/SpokenWOZ-Test-Audio-Fixed

View all activity

Organizations

liked 2 datasets 18 days ago

ssz1111/SpokenWOZ-Test-Audio

Viewer • Updated Jan 8 • 1k • 181 • 1

ssz1111/SpokenWOZ-Test-Audio-Fixed

Viewer • Updated Jan 8 • 1k • 124 • 1

liked a dataset 3 months ago

anyreach-ai/dualturn-otospeech-turn-taking

Viewer • Updated May 11 • 1.12k • 517 • 3

liked a dataset 5 months ago

sarulab-speech/J-CHAT

Viewer • Updated Feb 9, 2025 • 2.02k • 121 • 45

liked 2 datasets 6 months ago

otoearth/otoSpeech-full-duplex-processed-141h

Preview • Updated Feb 6 • 276 • 28

otoearth/otoSpeech-full-duplex-280h

Preview • Updated Feb 6 • 127 • 11

liked 8 models about 1 year ago

pyannote/speaker-diarization-3.1

Automatic Speech Recognition • Updated May 10, 2024 • 8.63M • 2.84k

pyannote/voice-activity-detection

Automatic Speech Recognition • Updated May 10, 2024 • 3.32M • 239

Qwen/Qwen2-Audio-7B-Instruct

Audio-Text-to-Text • 8B • Updated Jan 12, 2025 • 715k • 551

fixie-ai/ultravox-v0_5-llama-3_2-1b

Audio-Text-to-Text • 0.7B • Updated Mar 11 • 1.18M • 90

SWivid/F5-TTS

Text-to-Speech • Updated Mar 21, 2025 • 780k • 1.19k

hexgrad/Kokoro-82M

Text-to-Speech • Updated Apr 10, 2025 • 10.3M • • 6.58k

coqui/XTTS-v2

Text-to-Speech • Updated Dec 11, 2023 • 9.34M • 3.68k

nari-labs/Dia-1.6B

Text-to-Speech • 2B • Updated Jun 1, 2025 • 11.2k • • 2.9k