Search Results for author:
Found 25 papers, 2 papers with code
Unsupervised speech enhancement with diffusion-based generative models
To address this issue, we introduce an alternative approach that operates in an unsupervised manner, leveraging the generative power of diffusion models.
Progressive Learning for Systematic Design of Large Neural Networks
The developed network is expected to show good generalization power due to appropriate regularization and use of random weights in the layers.
Union of Low-Rank Subspaces Detector
The problem of signal detection using a flexible and general model is considered.
A Study on Clustering for Clustering Based Image De-Noising
In the present paper, we suggest a method based on global clustering of image constructing blocks.
Optimization of Clustering for Clustering-based Image Denoising
In this paper, the problem of de-noising of an image contaminated with additive white Gaussian noise (AWGN) is studied.
SSFN -- Self Size-estimating Feed-forward Network with Low Complexity, Limited Need for Human Intervention, and Consistent Behaviour across Trials
We design a self size-estimating feed-forward network (SSFN) using a joint optimization approach for estimation of number of layers, number of nodes and learning of weight matrices.
Audio-visual Speech Enhancement Using Conditional Variational Auto-Encoders
Variational auto-encoders (VAEs) are deep generative latent variable models that can be used for learning the distribution of complex data.
Robust Unsupervised Audio-visual Speech Enhancement Using a Mixture of Variational Autoencoders
When visual data is clean, speech enhancement with audio-visual VAE shows a better performance than with audio-only VAE, which is trained on audio-only data.
Mixture of Inference Networks for VAE-based Audio-visual Speech Enhancement
Two encoder networks input, respectively, audio and visual data, and the posterior of the latent variables is modeled as a mixture of two Gaussian distributions output from each encoder network.
Unsupervised Performance Analysis of 3D Face Alignment with a Statistically Robust Confidence Test
The results show that the proposed analysis is consistent with supervised metrics and that it can be used to measure the accuracy of both predicted landmarks and of automatically annotated 3DFA datasets, to detect errors and to eliminate them.
Deep Variational Generative Models for Audio-visual Speech Separation
To better utilize the visual information, the posteriors of the latent variables are inferred from mixed speech (instead of clean speech) as well as the visual data.
Face Frontalization Based on Robustly Fitting a Deformable Shape Model to 3D Landmarks
We propose to model inliers and outliers with the generalized Student's t-probability distribution function, a heavy-tailed distribution that is immune to non-Gaussian errors in the data.
Switching Variational Auto-Encoders for Noise-Agnostic Audio-visual Speech Enhancement
Recently, audio-visual speech enhancement has been tackled in the unsupervised settings based on variational auto-encoders (VAEs), where during training only clean data is used to train a generative model for speech, which at test time is combined with a noise model, e. g. nonnegative matrix factorization (NMF), whose parameters are learned without supervision.
The impact of removing head movements on audio-visual speech enhancement
This paper investigates the impact of head movements on audio-visual speech enhancement (AVSE).
A Sparsity-promoting Dictionary Model for Variational Autoencoders
Structuring the latent space in probabilistic deep generative models, e. g., variational autoencoders (VAEs), is important to yield more expressive models and interpretable representations, and to avoid overfitting.
Expression-preserving face frontalization improves visually assisted speech processing
The method alternates between the estimation of (i)~the rigid transformation (scale, rotation, and translation) and (ii)~the non-rigid deformation between an arbitrarily-viewed face and a face model.
Audio-visual speech enhancement with a deep Kalman filter generative model
Deep latent variable generative models based on variational autoencoder (VAE) have shown promising performance for audiovisual speech enhancement (AVSE).
A weighted-variance variational autoencoder model for speech enhancement
A zero-mean complex-valued Gaussian distribution is usually assumed for the generative model, where the speech information is encoded in the variance as a function of a latent variable.
Fast and efficient speech enhancement with variational autoencoders
Unsupervised speech enhancement based on variational autoencoders has shown promising performance compared with the commonly used supervised methods.
Diffusion-based speech enhancement with a weighted generative-supervised learning loss
Diffusion-based generative models have recently gained attention in speech enhancement (SE), providing an alternative to conventional supervised methods.
Posterior sampling algorithms for unsupervised speech enhancement with recurrent variational autoencoder
Nevertheless, the involved iterative variational expectation-maximization (VEM) process at test time, which relies on a variational inference method, results in high computational complexity.
End-to-end Multichannel Speaker-Attributed ASR: Speaker Guided Decoder and Input Feature Analysis
We present an end-to-end multichannel speaker-attributed automatic speech recognition (MC-SA-ASR) system that combines a Conformer-based encoder with multi-frame crosschannel attention and a speaker-attributed Transformer-based decoder.
End-to-end Joint Rich and Normalized ASR with a limited amount of rich training data
End-to-end (E2E) ASR models offer both convenience and the ability to perform such joint transcription of speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge
In this paper, we present the objective and subjective evaluations of the systems that were submitted to the CHiME-7 UDASE task, and we provide an analysis of the results.
Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications
Past studies on end-to-end meeting transcription have focused on model architecture and have mostly been evaluated on simulated meeting data.
