Skip to search formSkip to main contentSkip to account menu
SEGAN: Speech Enhancement Generative Adversarial Network
TLDR
This work proposes the use of generative adversarial networks for speech enhancement, and operates at the waveform level, training the model end-to-end, and incorporate 28 speakers and 40 different noise conditions into the same model, such that model parameters are shared across them.
View PDF on arXiv
Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks
TLDR
Experiments show that the proposed improved self-supervised method can learn transferable, robust, and problem-agnostic features that carry on relevant information from the speech signal, such as speaker identity, phonemes, and even higher-level features such as emotional cues.
View PDF on arXiv
Multi-Task Self-Supervised Learning for Robust Speech Recognition
TLDR
PASE+ is proposed, an improved version of PASE that better learns short- and long-term speech dynamics with an efficient combination of recurrent and convolutional networks and learns transferable representations suitable for highly mismatched acoustic conditions.
View on IEEE
Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion
TLDR
This paper proposes Blow, a single-scale normalizing flow using hypernetwork conditioning to perform many-to-many voice conversion between raw audio, and shows that Blow compares favorably to existing flow-based architectures and other competitive baselines, obtaining equal or better performance in both objective and subjective evaluations.
View PDF on arXiv
Towards a universal neural network encoder for time series
TLDR
This work studies the use of a time series encoder to learn representations that are useful on data set types with which it has not been trained on, and finds that such strategies are competitive with the state-of-the-art, often outperforming conceptually-matching approaches.
View PDF on arXiv
Wav2Pix: Speech-conditioned Face Generation Using Generative Adversarial Networks
TLDR
A deep neural network is proposed that is trained from scratch in an end-to-end fashion, generating a face directly from the raw speech waveform without any additional identity information (e.g reference image or one-hot encoding).
View on IEEE
Language and Noise Transfer in Speech Enhancement Generative Adversarial Network
TLDR
This work presents the results of adapting a speech enhancement generative adversarial network by fine-tuning the generator with small amounts of data, and investigates the minimum requirements to obtain a stable behavior in terms of several objective metrics in two very different languages.
View on IEEE
Towards Generalized Speech Enhancement with Generative Adversarial Networks
TLDR
This work extends a previous GAN-based speech enhancement system to deal with mixtures of four types of aggressive distortions, and proposes the addition of an adversarial acoustic regression loss that promotes a richer feature extraction at the discriminator.
View PDF on arXiv
SESQA: Semi-Supervised Learning for Speech Quality Assessment
TLDR
This work tackles automatic speech quality assessment with a semi-supervised learning approach, combining available annotations with programmatically generated data, and using 3 different optimization criteria together with 5 complementary auxiliary tasks.
View on IEEE
Time-domain speech enhancement using generative adversarial networks
View via Publisher
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License