Skip to search formSkip to main contentSkip to account menu
Semantic Image Inpainting with Deep Generative Models
TLDR
A novel method for semantic image inpainting, which generates the missing content by conditioning on the available data, and successfully predicts information in large missing regions and achieves pixel-level photorealism, significantly outperforming the state-of-the-art methods.
View on IEEE
Zero-Shot Voice Style Transfer with Only Autoencoder Loss
TLDR
A new style transfer scheme that involves only an autoencoder with a carefully designed bottleneck is proposed, which achieves state-of-the-art results in many-to-many voice conversion with non-parallel data and is the first to perform zero-shot voice conversion.
View PDF on arXiv
Semantic Image Inpainting with Perceptual and Contextual Losses
TLDR
A novel method for image inpainting based on a Deep Convolutional Generative Adversarial Network that can successfully predict semantic information in the missing region and achieve pixel-level photorealism, which is impossible by almost all existing methods.
Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation
TLDR
Joint optimization of masking functions and deep recurrent neural networks for monaural source separation tasks, including speech separation, singing voice separation, and speech denoising, and a discriminative criterion for training neural networks to further enhance the separation performance are explored.
View on ACM
Deep learning for monaural speech separation
TLDR
The joint optimization of the deep learning models (deep neural networks and recurrent neural networks) with an extra masking layer, which enforces a reconstruction constraint, is proposed to enhance the separation performance of monaural speech separation models.
View on IEEE
Dilated Recurrent Neural Networks
TLDR
This paper introduces a simple yet effective RNN connection structure, the DilatedRNN, characterized by multi-resolution dilated recurrent skip connections and introduces a memory capacity measure, the mean recurrent length, which is more suitable for RNNs with long skip connections than existing measures.
View PDF on arXiv
Singing-voice separation from monaural recordings using robust principal component analysis
TLDR
This paper proposes using robust principal component analysis for singing-voice separation from music accompaniment using a binary time-frequency masking method and shows that this method can achieve around 1~1.4 dB higher GNSDR compared with two state-of-the-art approaches without using prior training or requiring particular features.
View on IEEE
Singing-Voice Separation from Monaural Recordings using Deep Recurrent Neural Networks
TLDR
This paper explores using deep recurrent neural networks for singing voice separation from monaural recordings in a supervised setting and proposes jointly optimizing the networks for multiple source signals by including the separation step as a nonlinear operation in the last layer.
View via Publisher
Computational differences between whispered and non-whispered speech
Whispering is a common type of speech which is not often studied in speech technology. Perceptual and physiological studies show us that whispered speech is subtly different from phonated speech, and…
Vowel Contrast and Speech Intelligibility in Dysarthria
TLDR
A speaker’s overall intelligibility in dysarthric speech is better represented by the overlap degree among vowels than by the vowel space.
View on PubMed
...
...
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