Search Results for author:
Found 29 papers, 9 papers with code
Using fine-tuning and min lookahead beam search to improve Whisper
In addition to a lack of training data on low-resource languages, we identify some limitations in the beam search algorithm used in Whisper.
Cross-Utterance Conditioned VAE for Speech Generation
Experimental results on the LibriTTS datasets demonstrate that our proposed models significantly enhance speech synthesis and editing, producing more natural and expressive speech.
FaceChain: A Playground for Human-centric Artificial Intelligence Generated Content
In this paper, we present FaceChain, a personalized portrait generation framework that combines a series of customized image-generation model and a rich set of face-related perceptual understanding models (\eg, face detection, deep face embedding extraction, and facial attribute recognition), to tackle aforementioned challenges and to generate truthful personalized portraits, with only a handful of portrait images as input.
Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speech
Modelling prosody variation is critical for synthesizing natural and expressive speech in end-to-end text-to-speech (TTS) systems.
Perceptual Contrast Stretching on Target Feature for Speech Enhancement
Specifically, the contrast of target features is stretched based on perceptual importance, thereby improving the overall SE performance.
Ranked #5 on
Speech Enhancement
on VoiceBank + DEMAND
Conditional Diffusion Probabilistic Model for Speech Enhancement
Speech enhancement is a critical component of many user-oriented audio applications, yet current systems still suffer from distorted and unnatural outputs.
HASA-net: A non-intrusive hearing-aid speech assessment network
Without the need of a clean reference, non-intrusive speech assessment methods have caught great attention for objective evaluations.
OSSEM: one-shot speaker adaptive speech enhancement using meta learning
Although deep learning (DL) has achieved notable progress in speech enhancement (SE), further research is still required for a DL-based SE system to adapt effectively and efficiently to particular speakers.
SEOFP-NET: Compression and Acceleration of Deep Neural Networks for Speech Enhancement Using Sign-Exponent-Only Floating-Points
In this paper, a novel sign-exponent-only floating-point network (SEOFP-NET) technique is proposed to compress the model size and accelerate the inference time for speech enhancement, a regression task of speech signal processing.
MetricGAN-U: Unsupervised speech enhancement/ dereverberation based only on noisy/ reverberated speech
Most of the deep learning-based speech enhancement models are learned in a supervised manner, which implies that pairs of noisy and clean speech are required during training.
Mutual Information Continuity-constrained Estimator
Accordingly, we propose Mutual Information Continuity-constrained Estimator (MICE).
Diverse Similarity Encoder for Deep GAN Inversion
Current deep generative adversarial networks (GANs) can synthesize high-quality (HQ) images, so learning representation with GANs is favorable.
Speech Recovery for Real-World Self-powered Intermittent Devices
The incompleteness of speech inputs severely degrades the performance of all the related speech signal processing applications.
MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement
The discrepancy between the cost function used for training a speech enhancement model and human auditory perception usually makes the quality of enhanced speech unsatisfactory.
Ranked #12 on
Speech Enhancement
on VoiceBank + DEMAND
Global ill-posedness for a dense set of initial data to the Isentropic system of gas dynamics
In dimension $n=2$ and $3$, we show that for any initial datum belonging to a dense subset of the energy space, there exist infinitely many global-in-time admissible weak solutions to the isentropic Euler system whenever $1<\gamma\leq 1+\frac2n$.
Analysis of PDEs 35Q31, 76N10, 35L65
Dissipative solutions to the compressible isentropic Navier-Stokes equations
The existence of dissipative solutions to the compressible isentropic Navier-Stokes equations was established in this paper.
Analysis of PDEs
Inviscid limit of the inhomogeneous incompressible Navier-Stokes equations under the weak Kolmogorov hypothesis in $\mathbb{R}^3$
In this paper, we consider the inviscid limit of inhomogeneous incompressible Navier-Stokes equations under the weak Kolmogorov hypothesis in $\mathbb{R}^3$.
Analysis of PDEs
Attention-based multi-task learning for speech-enhancement and speaker-identification in multi-speaker dialogue scenario
In this study, we propose an attention-based MTL (ATM) approach that integrates MTL and the attention-weighting mechanism to simultaneously realize a multi-model learning structure that performs speech enhancement (SE) and speaker identification (SI).
Defending Against Universal Adversarial Patches by Clipping Feature Norms
Physical-world adversarial attacks based on universal adversarial patches have been proved to be able to mislead deep convolutional neural networks (CNNs), exposing the vulnerability of real-world visual classification systems based on CNNs.
Shaping Deep Feature Space towards Gaussian Mixture for Visual Classification
In this work, we propose a Gaussian mixture (GM) loss function for deep neural networks for visual classification.
Improving Speech Enhancement Performance by Leveraging Contextual Broad Phonetic Class Information
Experimental results from speech denoising, speech dereverberation, and impaired speech enhancement tasks confirmed that contextual BPC information improves SE performance.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Improving Perceptual Quality by Phone-Fortified Perceptual Loss using Wasserstein Distance for Speech Enhancement
Speech enhancement (SE) aims to improve speech quality and intelligibility, which are both related to a smooth transition in speech segments that may carry linguistic information, e. g. phones and syllables.
Ranked #12 on
Speech Enhancement
on VoiceBank + DEMAND
Multi-Scale Networks for 3D Human Pose Estimation with Inference Stage Optimization
Addressing these problems, we introduce a spatio-temporal network for robust 3D human pose estimation.
Boosting Objective Scores of a Speech Enhancement Model by MetricGAN Post-processing
The Transformer architecture has demonstrated a superior ability compared to recurrent neural networks in many different natural language processing applications.
Speech Enhancement based on Denoising Autoencoder with Multi-branched Encoders
The DSDT is built based on a prior knowledge of speech and noisy conditions (the speaker, environment, and signal factors are considered in this paper), where each component of the multi-branched encoder performs a particular mapping from noisy to clean speech along the branch in the DSDT.
Time-Domain Multi-modal Bone/air Conducted Speech Enhancement
Previous studies have proven that integrating video signals, as a complementary modality, can facilitate improved performance for speech enhancement (SE).
Increasing Compactness Of Deep Learning Based Speech Enhancement Models With Parameter Pruning And Quantization Techniques
In addition, a parameter quantization (PQ) technique was applied to reduce the size of a neural network by representing weights with fewer cluster centroids.
