Effective Mel-Spectrogram Synthesis for Multi-Speaker Text-to-Speech with Band-Specific Acoustic Modeling
Open Access
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 1
Abstract
No abstract availableFunding Information
- Chung-Ang University Graduate Research Scholarship
- Institute of Information and Communications Technology Planning and Evaluation (IITP) Grant funded by MSIT [Artificial Intelligence Graduate School Program (Chung-Ang University)] (RS-2021-II211341)
This publication has 20 references indexed in Scilit:
- DiffVoice: Text-to-Speech with Latent Diffusion2023
- Autotts: End-to-End Text-to-Speech Synthesis Through Differentiable Duration Modeling2023
- EfficientSpeech: An On-Device Text to Speech Model2023
- SC-CNN: Effective Speaker Conditioning Method for Zero-Shot Multi-Speaker Text-to-Speech SystemsIEEE Signal Processing Letters, 2023
- ProDiff2022
- Lightspeech: Lightweight and Fast Text to Speech with Neural Architecture Search2021
- Flow-TTS: A Non-Autoregressive Network for Text to Speech Based on Flow2020
- Neural Speech Synthesis with Transformer NetworkProceedings of the AAAI Conference on Artificial Intelligence, 2019
- A Continuous Vocoder Using Sinusoidal Model for Statistical Parametric Speech Synthesis2018
- Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions2018