Harmonic-Net: Fundamental Frequency and Speech Rate Controllable Fast Neural Vocoder-Reference-Cited by-同舟云学术

Harmonic-Net: Fundamental Frequency and Speech Rate Controllable Fast Neural Vocoder

Author:

Matsubara Keisuke¹^ORCID,Okamoto Takuma²^ORCID,Takashima Ryoichi¹^ORCID,Takiguchi Tetsuya¹^ORCID,Toda Tomoki³^ORCID,Kawai Hisashi²

Affiliation:

1. Graduate School of System Informatics, Kobe University, Kobe, Japan

2. National Institute of Information and Communications Technology, Kyoto, Japan

3. Information Technology Center, Nagoya University, Nagoya, Japan

Funder

Keisuke Matsubara was interning at NICT

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Acoustics and Ultrasonics,Computer Science (miscellaneous),Computational Mathematics

Link

Reference64 articles.

1. ClariNet: Parallel wave generation in end-to-end text-to-speech;ping;Proc Int Conf Learn Representations,0

Cited by 4 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. PeriodGrad: Towards Pitch-Controllable Neural Vocoder Based on a Diffusion Probabilistic Model;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

2. FIRNet: Fundamental Frequency Controllable Fast Neural Vocoder With Trainable Finite Impulse Response Filter;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

4. WaveNeXt: ConvNeXt-Based Fast Neural Vocoder Without ISTFT layer;2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU);2023-12-16