Speech Enhancement for a Noise-Robust Text-to-Speech Synthesis System Using Deep Recurrent Neural Networks

By Cassia Valentini-Botinhao, Xin Eric Wang, Shinji Takaki, Junichi Yamagishi. 2016

143 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. Yi Ren
5. Sheng Zhao
6. Jinglin Liu
7. Zhou Zhao
8. Frank K. Soong

In Signal Processing

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Yi Ren
5. Jinglin Liu
6. Sheng Zhao
7. Ross Cutler
8. Zhou Zhao

Citations in the corpus

• Audio Codec Enhancement with Generative Adversarial Networks (2020, methodology): “The dataset we used for speech [25] consisted of 30 speakers (15 male, 15 female) from the clean Voice Bank [26] dataset (popularly known as the VCTK).”
• Textless Speech-to-Speech Translation on Real Data (2021, neutral): “Speech enhancement can remove the acoustic condition variation when building TTS models with noisy data (Botinhao et al., 2016; Adiga et al., 2019).”
• Denoispeech: Denoising Text to Speech with Frame-Level Noise Modeling (2020, methodology): “A straight-forward way [1, 2, 3, 4] is to first de-noise the noisy speech with a pre-trained speech enhancement model [5], and then use the enhanced speech to train the TTS model.”
• A scalable noisy speech dataset and online subjective test framework (2019, unknown): “The Edinburgh dataset [13] is a wideband dataset with 16 hours of clean and noisy audio clips.”
• ICASSP 2022 Acoustic Echo Cancellation Challenge (2022, methodology): “For clean speech far end signals, we use the speech segments from the Edinburgh dataset [14].”
• Speech Enhancement of Noisy and Reverberant Speech for Text-to-Speech (2018, methodology): “In a follow-up experiment [25] we compared using an RNN to enhance the TTS-style vocoder domain as in [23] and”
• Improved Speech Enhancement with the Wave-U-Net (2018, background): “With respect to the training set, 40 different noise conditions are considered [9, 16].”
• Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech (2016, unknown): “We argued in [12] that enhancing the acoustic parameters that are used for TTS acoustic model training would generate better synthetic voices as it would not require waveform reconstruction.”