📑

AI Paper Research

AI 논문 조사 및 정리

Foundations
음성·오디오Audio & Speech
Neural Codec Language Models are Zero-Sh...MusicLM: Generating Music From TextBark: Text-Prompted Generative Audio Mod...
Robust Speech Recognition via Large-Scal...AudioLM: a Language Modeling Approach to...High Fidelity Neural Audio Compression
HuBERT: Self-Supervised Speech Represent...SoundStream: An End-to-End Neural Audio ...
Natural TTS Synthesis by Conditioning Wa...
WaveNet: A Generative Model for Raw Audi...
홈/음성·오디오/2018

음성·오디오 — 2018

1편의 논문

ICASSP 20185,000+

Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions

멜 스펙트로그램 예측 기반 WaveNet 조건부 자연 TTS 합성

Jonathan Shen, Ruoming Pang, Ron J. Weiss et al. (2018)

← 음성·오디오 전체