Research Team at rinna Co., Ltd.

Publications

2024

PSLM: Parallel Generation of Text and Speech with LLMs for Low-Latency Spoken Dialogue Systems
Release of Pre-Trained Models for the Japanese Language

2023

An Integration of Pre-Trained Speech and Language Models for End-to-End Speech Recognition
Towards human-like spoken dialogue generation between AI agents from written dialogue
Focused Prefix Tuning for Controllable Text Generation
UniFLG: Unified Facial Landmark Generator from Text or Speech
Text-Guided Scene Sketch-to-Photo Synthesis

2022

Backchannel Generation Model for a Third Party Listener Agent
End-to-End Text-to-Speech Based on Latent Representation of Speaking Styles Using Spontaneous Dialogue

2021

MSR-NV: Neural Vocoder Using Multiple Sampling Rates

Pre-Trained Models

Benchmarks

Others

Neural Audio Codecベースの音声合成モデル性能改善手法に関する検討