Search Results - "Wang, Deliang"

Ideal ratio mask estimation using deep neural networks for robust speech recognition by Narayanan, Arun, DeLiang Wang

“…We propose a feature enhancement algorithm to improve robust automatic speech recognition (ASR). The algorithm estimates a smoothed ideal ratio mask (IRM) in…”
Get full text

Towards Scaling Up Classification-Based Speech Separation by Wang, Yuxuan, Wang, DeLiang

“…Formulating speech separation as a binary classification problem has been shown to be effective. While good separation performance is achieved in matched test…”
Get full text

On Training Targets for Supervised Speech Separation by Yuxuan Wang, Narayanan, Arun, DeLiang Wang

“…Formulation of speech separation as a supervised learning problem has shown considerable promise. In its simplest form, a supervised learning algorithm,…”
Get full text

Investigation of Speech Separation as a Front-End for Noise Robust Speech Recognition by Narayanan, Arun, DeLiang Wang

“…Recently, supervised classification has been shown to work well for the task of speech separation. We perform an in-depth evaluation of such techniques as a…”
Get full text

Achieving Color‐Tunable and Time‐Dependent Organic Long Persistent Luminescence via Phosphorescence Energy Transfer for Advanced Anti‐Counterfeiting by Wang, Deliang, Gong, Junyi, Xiong, Yu, Wu, Hongzhuo, Zhao, Zheng, Wang, Dong, Tang, Ben Zhong

“…Organic ultralong room‐temperature phosphorescence (RTP) materials have promising applications in anti‐counterfeiting. To improve the encryption level, the…”
Get full text

Complex Ratio Masking for Monaural Speech Separation by Williamson, Donald S., Wang, Yuxuan, Wang, DeLiang

“…Speech separation systems usually operate on the short-time Fourier transform (STFT) of noisy speech, and enhance only the magnitude spectrum while leaving the…”
Get full text

Time-Frequency Masking in the Complex Domain for Speech Dereverberation and Denoising by Williamson, Donald S., Wang, DeLiang

“…In real-world situations, speech is masked by both background noise and reverberation, which negatively affect perceptual quality and intelligibility. In this…”
Get full text

Deep Learning Based Binaural Speech Separation in Reverberant Environments by Zhang, Xueliang, Wang, DeLiang

“…Speech signal is usually degraded by room reverberation and additive noises in real environments. This paper focuses on separating target speech signal in…”
Get full text

Features for Masking-Based Monaural Speech Separation in Reverberant Conditions by Delfarah, Masood, DeLiang Wang

“…Monaural speech separation is a fundamental problem in speech and signal processing. This problem can be approached from a supervised learning perspective by…”
Get full text

Exploring Monaural Features for Classification-Based Speech Segregation by Wang, Yuxuan, Han, Kun, Wang, DeLiang

“…Monaural speech segregation has been a very challenging problem for decades. By casting speech segregation as a binary classification problem, recent advances…”
Get full text

Factorization-Based Texture Segmentation by Jiangye Yuan, Deliang Wang, Cheriyadat, Anil M.

“…This paper introduces a factorization-based approach that efficiently segments textured images. We use local spectral histograms as features, and construct an…”
Get full text

Towards Model Compression for Deep Learning Based Speech Enhancement by Tan, Ke, Wang, DeLiang

“…The use of deep neural networks (DNNs) has dramatically elevated the performance of speech enhancement over the last decade. However, to achieve strong…”
Get full text

A classification based approach to speech segregation by Han, Kun, Wang, DeLiang

“…A key problem in computational auditory scene analysis (CASA) is monaural speech segregation, which has proven to be very challenging. For monaural mixtures,…”
Get full text

An Unsupervised Approach to Cochannel Speech Separation by Hu, Ke, Wang, DeLiang

“…Cochannel (two-talker) speech separation is predominantly addressed using pretrained speaker dependent models. In this paper, we propose an unsupervised…”
Get full text

Complex Spectral Mapping for Single- and Multi-Channel Speech Enhancement and Robust ASR by Wang, Zhong-Qiu, Wang, Peidong, Wang, DeLiang

“…This study proposes a complex spectral mapping approach for single- and multi-channel speech enhancement, where deep neural networks (DNNs) are used to predict…”
Get full text

A Tandem Algorithm for Pitch Estimation and Voiced Speech Segregation by Hu, Guoning, Wang, DeLiang

“…A lot of effort has been made in computational auditory scene analysis (CASA) to segregate speech from monaural mixtures. The performance of current CASA…”
Get full text

On Adversarial Training and Loss Functions for Speech Enhancement by Pandey, Ashutosh, Wang, Deliang

“…Generative adversarial networks (GANs) are becoming increasingly popular for image processing tasks. Researchers have started using GAN s for speech…”
Get full text

Time-Frequency Masking for Speech Separation and Its Potential for Hearing Aid Design by Wang, DeLiang

“…A new approach to the separation of speech from speech-in-noise mixtures is the use of time-frequency (T-F) masking. Originated in the field of computational…”
Get full text

Robust Speaker Identification in Noisy and Reverberant Conditions by Zhao, Xiaojia, Wang, Yuxuan, Wang, DeLiang

“…Robustness of speaker recognition systems is crucial for real-world applications, which typically contain both additive noise and room reverberation. However,…”
Get full text

On Cross-Corpus Generalization of Deep Learning Based Speech Enhancement by Pandey, Ashutosh, Wang, DeLiang

“…In recent years, supervised approaches using deep neural networks (DNNs) have become the mainstream for speech enhancement. It has been established that DNNs…”
Get full text