SaruLab Speech group

sarulab-speech's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

trgkpc 

updated a model 10 days ago

sarulab-speech/SpatialCLAP

Updated 10 days ago • 12 • 1

Wataru 

updated a model 19 days ago

sarulab-speech/sidon-v0.1

Updated 19 days ago • 12

Wataru 

updated a model 21 days ago

sarulab-speech/sidon_raw_weight

Updated 21 days ago • 107

Wataru 

published a model 21 days ago

sarulab-speech/sidon_raw_weight

Updated 21 days ago • 107

Wataru 

updated a dataset 28 days ago

sarulab-speech/yodas2_sidon

Viewer • Updated 28 days ago • 1.46M • 22k • 51

Wataru 

authored 3 papers 3 months ago

UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022

Paper • 2204.02152 • Published Apr 5, 2022

The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech

Paper • 2409.09305 • Published Sep 14, 2024

Sidon: Fast and Robust Open-Source Multilingual Speech Restoration for Large-scale Dataset Cleansing

Paper • 2509.17052 • Published Sep 21, 2025 • 2

Wataru 

authored a paper over 1 year ago

J-CHAT: Japanese Large-scale Spoken Dialogue Corpus for Spoken Dialogue Language Modeling

Paper • 2407.15828 • Published Jul 22, 2024

Wataru 

updated 2 models almost 2 years ago

sarulab-speech/UTDUSS-Vocoder

Updated Mar 20, 2024 • 2

sarulab-speech/hubert-base-jtube

Feature Extraction • Updated Feb 5, 2024 • 30 • 16

Wataru 

updated a Space almost 2 years ago

Running on Zero

11

CoCoCap Beta

🐠

11

Transcribe Japanese audio to text

Wataru 

updated a Space about 2 years ago

Running

18

UTMOS Demo

🐢

18

Evaluate audio quality with MOS score

Wataru 

updated a dataset almost 4 years ago

sarulab-speech/bvcc-voicemos2022

Updated Feb 25, 2022 • 14