sarulab-speech

jtubespeech

UTMOS22

UT-Sarulab MOS prediction system using SSL models

jsut-label

context labels and pronunciation data for JSUT corpus

xvector_jtubespeech

xvector model on jtubespeech

whisper-asr-finetune

lightweight_spkr_anon

Lightweight speaker anonymization [IEEE SLT2021]

multi-speaker-dgp

Official implementation of DGP-based multi-speaker speech synthesis with PyTorch

tdmelodic_openjtalk

tdmelodic for open-jtalk

Coco-Nut

Coco-Nut (Corpus of connecting NIHONGO utterance and text) corpus

spatial_voice_conversion

Spatial Voice Conversion: Voice Conversion Preserving Spatial Information and Non-target Signals

ml-audiocaps

Multi-lingual AudioCaps

visual-onoma-to-wave

Visual onoma-to-wave official implementation

VMC2024-sarulab-data

Mid-Attribute-Speaker-Generation

pseudo_speech_decryption

demo_CALLS_corpus

CALLS: Japanese Empathetic Dialogue Speech Corpus of Complaint Handling and Attentive Listening in Customer Center (INTERSPEECH2023)

demo_ChatGPT_EDSS

ChatGPT-EDSS: Empathetic Dialogue Speech Synthesis Trained from ChatGPT-derived Context Word Embeddings (INTERSPEECH2023)

bert-japanese

BERT models for Japanese text.

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

SaSLaW

Dialogue Speech Corpus with Audio-visual Egocentric Information, "So, what are you Speaking, Listening, and Watching?"