An Investigation of Subband Wavenet Vocoder Covering Entire Audible Frequency Range with Limited Acoustic Features

By Takuma Okamoto, Kentaro Tachibana, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai. 2018

24 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Frank K. Soong
5. Lei He
6. Dong Yu
7. Jinyu Li
8. Chao Weng

In Signal Processing

1. Xu Tan
2. Tie-Yan Liu
3. Tao Qin
4. Frank K. Soong
5. Lei He
6. Dong Yu
7. Hisashi Kawai
8. Jinyu Li

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, methodology): “Typical models include DurIAN [411], multi-band MelGAN [400], subband WaveNet [244], and multi-band LPCNet [342].”
• An Efficient Subband Linear Prediction for LPCNet-Based Neural Synthesis (2020, background): “The WaveNet vocoder models the probability distribution of the speech sequence p ( x ; h ) conditioned on the product of the history sequence distribution, given acoustic features h , as: ( In a multirate system, the speech is decomposed into several subband streams through analysis filter banks and ”
• DurIAN: Duration Informed Attention Network For Multimodal Synthesis (2019, background): “While several studies [24, 25] have explored the usage of multi-band strategy for neural vocoder, these studies aim at modeling audio with higher sampling rate by training separate neural vocoder models for each subband.”
• DurIAN: Duration Informed Attention Network for Speech Synthesis (2020, methodology): “Existing approaches [23, 24] utilizing such charactertistics of multiband processing is to model each subband with separatly trained neural vocoder which will then be inferenced in parallel using mulitple CPUs or GPUs.”
• Triple M: A Practical Text-to-Speech Synthesis System with Multi-Guidance Attention and Multi-Band Multi-Time LPCNet (2021, methodology): “Multi-band processing is initially used for parallel acceleration of vocoder [16, 17].”
• FeatherWave: An efficient high-fidelity neural vocoder with multi-band linear prediction (2020, methodology): “with the technique of subband [12, 13] to improve generation speed.”
• Improving FFTNet Vocoder with Noise Shaping and Subband Approaches (2018, methodology): “In particular, the subband FFTNet vocoders can realize more than M = 4 times faster generation as a result of the decimation and smaller network, as in subband WaveNet [46,47].”