Speech Enhancement Using Bayesian Wavenet

By Kaizhi Qian, Yang Zhang, Shiyu Chang, Xuesong Yang, Dinei A. F. Florêncio, Mark Hasegawa-Johnson. 2017

85 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

In Signal Processing

Citations in the corpus

Speech Denoising with Deep Feature Losses (2018, background): “sults in speech processing [19, 20] including speech denoising [21, 22, 23, 24].”
A Wavenet for Speech Denoising (2017, methodology): “[14] used a Bayesian Wavenet for speech denoising.”
End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction (2018, background): “Another recent trend is to avoid the phase inconsistency problem altogether by operating in the time domain, using convolutional neural networks [30, 31], WaveNet [32], generative adversarial networks [33], or encoder-decoder architectures [34].”
End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networks (2017, background): “In fact, other waveform enhancement frameworks based on generative adversarial networks (GANs) [25] and WaveNet [42, 43] were also shown to outperform conventional models.”
A New Framework for CNN-Based Speech Enhancement in the Time Domain (2019, background): “The proposed model in [16] is very slow, and in [17], it operates at the frame level for efficiency and hence suffers from the same problem.”
Conditional Diffusion Probabilistic Model for Speech Enhancement (2022, background): “Well-known examples along this direction include generative adversarial networks (GANs) [11, 12], Bayesian wavenet [13], variational autoencoders [14], and flow-based models [15].”
Speech Enhancement of Noisy and Reverberant Speech for Text-to-Speech (2018, background): “based systems [52], [53] and convolutional neural networks [54], [55].”
A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI (2023, unknown): “A discriminative method minimizes the difference between enhanced and clean speech [13, 16, 17, 42], while generative models are optimized by estimating the distribution of clean signals [51, 80, 86, 106, 108].”
Deep Learning for Environmentally Robust Speech Recognition (2017, background): “des an opportunity to directly map the noisy speech to clean speech in temporal domain, which is supposed to retain the complete speech information (including phase). Two exemplary works are shown in [79] and [80]. Particularly in [79], an explicit prior model that learns the conditional distributio”