Wang, Deliang, Wang, Jianguo, Dong, Xiaobo
Results are presented of extended and refined optical identification of 181 radio/X-ray sources in the RASS-Green Bank (RGB) catalog which have been spectroscopically observed in the Sloan digital...
SPEECH RECOGNITION IN MULTISOURCE REVERBERANT ENVIRONMENTS WITH BINAURAL INPUTS (2009)
Nicoleta Roman, Soundararajan Srinivasan, Deliang Wang
We present a binaural solution to robust speech recognition in multi-source reverberant environments. We employ the notion of an ideal time-frequency binary mask, which selects the target if it is...
INCORPORATING AUDITORY FEATURE UNCERTAINTIES IN ROBUST SPEAKER IDENTIFICATION (2009)
Yang Shao, Soundararajan Srinivasan, Deliang Wang
Conventional speaker recognition systems perform poorly under noisy conditions. Recent research suggests that binary timefrequency (T-F) masks be a promising front-end for robust speaker recognition....
Musical Sound Separation Based on Binary Time-Frequency Masking (2009)
The problem of overlapping harmonics is particularly acute in musical sound separation and has not been addressed adequately. We propose a monaural system based on binary time-frequency masking with...
Musical Sound Separation Based on Binary Time-Frequency Masking (2009)
The problem of overlapping harmonics is particularly acute in musical sound separation and has not been addressed adequately. We propose a monaural system based on binary time-frequency masking with...
APitch-Based Method forthe Estimation of Short Reverberation Time (2008)
PACS no. 43.55.Mc
A Computational Auditory Scene Analysis System for Robust Speech Recognition (2008)
Soundararajan Srinivasan, Yang Shao, Zhaozhang Jin, Deliang Wang
We present a computational auditory scene analysis system for separating and recognizing target speech in the presence of competing speech or noise. We estimate, in two stages, the ideal binary...
Separating underdetermined convolutive speech mixtures (2008)
Michael Syskind Pedersen, Deliang Wang, Ulrik Kjems
Abstract. A limitation in many source separation tasks is that the number of source signals has to be known in advance. Further, in order to achieve good performance, the number of sources cannot...
Transforming Binary Uncertainties for Robust Speech Recognition (2008)
Soundararajan Srinivasan, Deliang Wang
Abstract—Recently, several algorithms have been proposed to enhance noisy speech by estimating a binary mask that can be used to select those time–frequency regions of a noisy speech signal that...
EXPLOITING UNCERTAINTIES FOR BINAURAL SPEECH RECOGNITION (2008)
Soundararajan Srinivasan, Nicoleta Roman, Deliang Wang
Recently several algorithms have been proposed to enhance noisy speech by estimating the signal-to-noise ratio (SNR) within a local time-frequency region based on binaural cues of interaural time and...
An Oscillatory Correlation Model of Auditory Streaming (2008)
We present a neurocomputational model for auditory streaming, which is a prominent phenomenon of auditory scene analysis. The proposed model represents auditory scene analysis by oscillatory...
A Binaural Auditory Model for Missing Data Recognition of Speech in Noise (2008)
Kalle J. Palomäki, Guy J. Brown, Deliang Wang
We describe a binaural auditory model for speech recognition, which is robust in the presence of reverberation and spatially separated noise intrusions. The principle underlying the model is to...
Soundararajan Srinivasan, Yang Shao, Zhaozhang Jin, Deliang Wang
We present a computational auditory scene analysis system for separating and recognizing target speech in the presence of competing speech or noise. We estimate, in two stages, the ideal binary...
12 An Auditory Scene Analysis Approach to Monaural Speech Segregation (2008)
A human listener has the remarkable ability to segregate an acoustic mixture and attend to a target sound. This perceptual process is called auditory scene analysis (ASA). Moreover, the listener can...
16 Separation of Speech by Computational Auditory Scene Analysis (2008)
Abstract. The term auditory scene analysis (ASA) refers to the ability of human listeners to form perceptual representations of the constituent sources in an acoustic mixture, as in the well-known...
Two-Microphone Separation of Speech Mixtures (2008)
Michael Syskind Pedersen, Deliang Wang, Jan Larsen, Senior Member, Ulrik Kjems
Abstract—Separation of speech mixtures, often referred to as the cocktail party problem, has been studied for decades. In many source separation tasks, the separation method is limited by the...
On Intrinsic Generalization of Low Dimensional Representations of Images for Recognition (2008)
Xiuwen Liu, Anuj Srivastava, Deliang Wang
Abstract — Low dimensional representations of images impose equivalence relations in the image space; the induced equivalence class of an image is named as its intrinsic generalization. The...
in conjunctive visual search (2008)
Árni Kristjánsson, Árni Kristjánsson, Deliang Wang
The role of priming
Image and Texture Segmentation Using Local Spectral Histograms (2008)
Abstract—We present a method for segmenting images consisting of texture and nontexture regions based on local spectral histograms. Defined as a vector consisting of marginal distributions of...
BBS Commentary On the Computational Basis of Synchronized Codes (2008)
For scene analysis, it is important to ask the question of how synchronized population codes- the basic representation employed in the target article- are generated. Recent computational advances...
Two-microphone Separation of Speech Mixtures (2008)
Michael Syskind Pedersen, Deliang Wang, Jan Larsen, Senior Member, Ulrik Kjems
Abstract—Separation of speech mixtures, often referred to as the cocktail party problem, has been studied for decades. In many source separation tasks, the separation method is limited by the...
Book Review Unsupervised Learning- Foundations of Neural Computation (2008)
Edited Geoffrey Hinton, Terrence J. Sejnowski, Deliang Wang
The resurgence of the field of neural networks in the 1980's was primarily fueled by supervised learning, exemplified by the backpropagation algorithm. In supervised learning, a desired output...
A Computational Auditory Scene Analysis System for Robust Speech Recognition (2008)
Soundararajan Srinivasan, Yang Shao, Zhaozhang Jin, Deliang Wang
We present a computational auditory scene analysis system for separating and recognizing target speech in the presence of competing speech or noise. We estimate, in two stages, the ideal binary...
Separating underdetermined convolutive speech mixtures (2008)
Michael Syskind Pedersen, Deliang Wang, Jan Larsen, Ulrik Kjems
Abstract. A limitation in many source separation tasks is that the number of source signals has to be known in advance. Further, in order to achieve good performance, the number of sources cannot...
We use a locally excitatory globally inhibitory oscillator network (LEGION) as a framework for range image segmentation. Each oscillator in the LEGION network has excitatory lateral connections to...
Texture Classication Using Spectral Histograms (2007)
Xiuwen Liu, Xiuwen Liu, Deliang Wang, Deliang Wang
Abstract | Based on a local spatial/frequency representation, we propose a spectral histogram as a feature statistic for characterizing texture appearance. The spectral histogram consists of marginal...
Anticipation Model for Sequential Learning of Complex Sequences* (2007)
One of the fundamental aspects of human intelligence is the ability to process temporal information (Lashley, 1951). Learning and reproducing temporal se-quences are closely associated with our...
Book Review Unsupervised Learning- Foundations of Neural Computation (2007)
Edited Geoffrey Hinton, Terrence J. Sejnowski, Deliang Wang
The resurgence of the field of neural networks in the 1980's was primarily fueled by supervised learning, exemplified by the backpropagation algorithm. In supervised learning, a desired output...
Jeffrey J. Fox, Ciriyam Jayaprakash, Deliang Wang, Shannon R. Campbell
We study locally coupled networks of relaxation oscillators with excitatory connections and conduction delays and propose a mechanism for achieving zero phase-lag synchrony. Our mechanism is based on...
Deliang Wang, Arni Kristjansson, Ken Nakayama
Two types of mechanisms have dominated theoretical accounts of efficient visual search. First are bottom-up processes related to the hypothesized characteristics of retinotopic feature maps. Second...
Latent Semantic Analysis (2006)
Latent semantic analysis (LSA) is a model of human knowledge representation that approximates semantic relatedness judgments. It is a fully automatic mathematical/statistical technique for extracting...
Two-microphone Separation of Speech Mixtures (2006)
Syskind Pedersen, Michael, Wang, DeLiang, Larsen, Jan, Kjems, Ulrik
Separation of speech mixtures, often referred to as the ocktail party problem, has been studied for decades. In many source separation tasks, the separation method is limited by the assumption of at...
Separating Underdetermined Convolutive Speech Mixtures (2006)
Pedersen, Michael, Wang, DeLiang, Larsen, Jan, Kjems, Ulrik
A limitation in many source separation tasks is that the number of source signals has to be known in advance. Further, in order to achieve good performance, the number of sources cannot exceed the...
Model-based sequential organization in cochannel speech (2006)
Yang Shao, Student Member, Deliang Wang
Abstract—A human listener has the ability to follow a speaker’s voice while others are speaking simultaneously; in particular, the listener can organize the time–frequency energy of the same...
A two-stage algorithm for onemicrophone reverberant speech enhancement (2006)
Abstract—Under noise-free conditions, the quality of reverberant speech is dependent on two distinct perceptual components: coloration and long-term reverberation. They correspond to two physical...
Separation of singing voice from music accompaniment for monaural recordings (2006)
Yipeng Li, Student Member, Deliang Wang
Abstract—Separating singing voice from music accompaniment is very useful in many applications, such as lyrics recognition and alignment, singer identification, and music information retrieval....
Overcomplete Blind Source Separation by Combining ICA and Binary Time-Frequency Masking (2005)
Pedersen, Michael S., Wang, DeLiang, Larsen, Jan, Kjems, Ulrik
A limitation in many source separation tasks is that the number of source signals has to be known in advance. Further, in order to achieve good performance, the number of sources cannot exceed the...
Overcomplete blind source separation by combining ICA and binary time-frequency masking (2005)
Michael Syskind Pedersen, Deliang Wang, Jan Larsen, Ulrik Kjems
A limitation in many source separation tasks is that the number of source signals has to be known in advance. Further, in order to achieve good performance, the number of sources cannot exceed the...
Overcomplete blind source separation by combining ICA and binary time-frequency masking (2005)
Michael Syskind Pedersen, Deliang Wang, Jan Larsen, Ulrik Kjems
A limitation in many source separation tasks is that the number of source signals has to be known in advance. Further, in order to achieve good performance, the number of sources cannot exceed the...
On ideal binary mask as the computational goal of auditory scene analysis (2005)
What is the computational goal of auditory scene analysis? This is a key issue to address in the Marrian information-processing framework. It is also an important question for researchers in...
Monaural speech segregation based on pitch tracking and amplitude modulation (2004)
Speech segregation is an important task of auditory scene analysis (ASA), in which the speech of a certain speaker is separated from other interfering signals. Wang and Brown proposed a multistage...
Synchronization rates in classes of relaxation oscillators (2004)
Shannon R. Campbell, Deliang Wang, Ciriyam Jayaprakash
Abstract—Relaxation oscillators arise frequently in physics, electronics, mathematics, and biology. Their mathematical definitions possess a high degree of flexibility in the sense that through...
A multipitch tracking algorithm for noisy speech (2003)
We present a robust algorithm for multi-pitch tracking of noisy speech. Our approach integrates an improved channel and peak selection method, a new integration method for extracting periodicity...
A multipitch tracking algorithm for noisy speech (2003)
We present a robust algorithm for multi-pitch tracking of noisy speech. Our approach integrates an improved channel and peak selection method, a new integration method for extracting periodicity...
A multipitch tracking algorithm for noisy speech (2003)
Mingyang Wu, Student Member, Deliang Wang, Senior Member, Guy J. Brown
Abstract—An effective multipitch tracking algorithm for noisy speech is critical for acoustic signal processing. However, the performance of existing algorithms is not satisfactory. In this paper,...
Speech segregation based on sound localization (2003)
We study the cocktail-party effect, which refers to the ability of a listener to attend to a single talker in the presence of adverse acoustical conditions. It has been observed that this ability...
Intrinsic generalization analysis of low dimensional representations (2003)
Xiuwen Liu, Anuj Srivastava, Deliang Wang
Abstract — Low dimensional representations of images impose equivalence relations in the image space; the induced equivalence class of an image is named as its intrinsic generalization. The...
A classification-based cocktail party processor (2003)
Nicoleta Roman, Deliang Wang, Guy J. Brown
At a cocktail party, a listener can selectively attend to a single voice and filter out other acoustical interferences. How to simulate this perceptual ability remains a great challenge. This paper...
A classification-based cocktail party processor (2003)
Nicoleta Roman, Deliang Wang, Guy J. Brown
At a cocktail party, a listener can selectively attend to a single voice and filter out other acoustical interferences. How to simulate this perceptual ability remains a great challenge. This paper...
Texture classification using spectral histograms (2003)
Xiuwen Liu, Deliang Wang, Senior Member, Senior Member
Abstract—Based on a local spatial/frequency representation,we employ a spectral histogram as a feature statistic for texture classification. The spectral histogram consists of marginal...
A classification-based cocktail party processor (2003)
Nicoleta Roman, Deliang Wang, Guy J. Brown
At a cocktail party, a listener can selectively attend to a single voice and filter out other acoustical interferences. How to simulate this perceptual ability remains a great challenge. This paper...
Location-based sound segregation (2002)
Abstract – We propose and test a novel location-based approach for speech segregation. Within a narrow frequency band modifications to the relative energy of the target source with respect to the...
Location-based sound segregation (2002)
Abstract – We propose and test a novel location-based approach for speech segregation. Within a narrow frequency band modifications to the relative energy of the target source with respect to the...
Location-based sound segregation (2002)
Nicoleta Roman, Deliang Wang, Guy J. Brown
At a cocktail party, we can selectively attend to a single voice and filter out all the other acoustical interferences. How to simulate this perceptual ability remains a great challenge. This paper...
Monaural speech separation (2002)
Monaural speech separation has been studied in previous systems that incorporate auditory scene analysis principles. A major problem for these systems is their inability to deal with speech in the...
Scene analysis by integrating primitive segmentation and associative memory (2002)
Deliang Wang, Senior Member, Xiuwen Liu, Associate Member
Abstract—Scene analysis is a major aspect of perception and continues to challenge machine perception. This paper addresses the scene-analysis problem by integrating a primitive segmentation stage...
A binaural model for missing data speech recognition in noisy and reverberant conditions (2001)
Kalle J. Palomäki, Guy J. Brown, Deliang Wang
We describe a binaural auditory model for speech recognition, which is robust in the presence of reverberation and spatially separated noise intrusions. The principle underlying the model is to...
Xiuwen Liu, Ke Chen, Deliang Wang
Abstract—We propose a framework for object extraction with accurate boundaries. A multilayer perceptron is used to identify seed points through examples, and regions are extracted and localized...
A neural oscillator sound separator for missing data speech recognition (2001)
Guy J. Brown, Jon Barker, Deliang Wang
In order to recognise speech in a background of other sounds, human listeners must solve two perceptual problems. First, the mixture of sounds reaching the ears must be parsed to recover a...
A comparison of auditory and blind separation techniques for speech segregation (2001)
Abstract—A fundamental problem in auditory and speech processing is the segregation of speech from concurrent sounds. This problem has been a focus of study in computational auditory scene analysis...
Xiuwen Liu, Ke Chen, Deliang Wang
Abstract—We propose a framework for object extraction with accurate boundaries. A multilayer perceptron is used to identify seed points through examples, and regions are extracted and localized...
Perceiving geometric patterns: from spirals to inside-outside relations (2001)
Ke Chen, Deliang Wang, Senior Member, Senior Member
Abstract—Since first proposed by Minsky and Papert, the spiral problem is well known in neural networks. It receives much attention as a benchmark for various learning algorithms. Unlike previous...
A spectral histogram models for textons and texture discrimination (2001)
Based on a local spatial/frequency representation, the spectral histogram of an image is defined as the marginal distribution of responses from a bank of filters. We propose the spectral histogram as...
A neural oscillator sound separator for missing data speech recognition (2001)
Guy J. Brown, Jon Barker, Deliang Wang
In order to recognise speech in a background of other sounds, human listeners must solve two perceptual problems. First, the mixture of sounds reaching the ears must be parsed to recover a...
Appearance-based recognition using perceptual components (2001)
A fundamental problem with appearance-based recognition is how to encode the perceptual similarity between images as images need to be grouped based on their perceptual similarity. In this paper, we...
Weight adaptation and oscillatory correlation for image segmentation (2000)
Ke Chen, Deliang Wang, Xiuwen Liu
Abstract—We propose a method for image segmentation based on a neural oscillator network. Unlike previous methods, weight adaptation is adopted during segmentation to remove noise and preserve...
Weight adaptation and oscillatory correlation for image segmentation (2000)
Ke Chen, Deliang Wang, Xiuwen Liu
Abstract—We propose a method for image segmentation based on a neural oscillator network. Unlike previous methods, weight adaptation is adopted during segmentation to remove noise and preserve...
Motion segmentation based on motion/brightness integration and oscillatory correlation (2000)
Erdogan Çesmeli, Deliang Wang, Associate Member
Abstract—A segmentation method based on the integration of motion and brightness is proposed for image sequences. The method is composed of two parallel pathways that process motion and brightness,...
A Comparison of Auditory and Blind Separation Techniques for Speech Segregation (2000)
A fundamental problem in auditory and speech processing is the segregation of speech from concurrent sounds. This problem has been a focus of study in computational auditory scene analysis (CASA),...
Object selection based on oscillatory correlation (1999)
One of the classical topics in neural networks is winner-take-all (WTA), which has been widely used in unsupervised (competitive) learning, cortical processing, and attentional control. Because of...
Neural Scene Segmentation by Oscillatory Correlation (1998)
The segmentation of a visual scene into a set of coherent patterns (objects) is a fundamental aspect of perception, which underlies a variety of important tasks such as figure/ground segregation, and...
Computational Auditory Scene Analysis Based Perceptual and Neural Principles (1998)
A remarkable feat of the auditory system is its ability to disentangle the acoustic mixture and group the acoustic energy from the same event. This fundamental process of auditory perception is...
Relaxation oscillations exhibiting more than one time scale arise naturally from many physical systems. This paper proposes a method to numerically integrate large systems of relaxation oscillators....
Extracting Hydrographic Objects from Satellite Images Using a Two-layer Neural Network (1998)
Xiuwen Liu, DeLiang Wang, J. Raul Ramirez
This paper presents a two-layer network for extracting hydrographic objects, such as rivers, from satellite images. The first layer is a locally connected network, which performs nonlinear smoothing....
Xiuwen Liu, DeLiang Wang, J. Raul Ramirez
In this paper we use a two-layer neural network for robust image segmentation. The first layer is a locally coupled recurrent network. Using probabilistic measures, contextual information is...
Boundary Detection by Contextual Nonlinear Smoothing (1998)
Xiuwen Liu, DeLiang Wang, J. Raul Ramirez
In this paper we present a two-step boundary detection algorithm. The first step is a nonlinear smoothing algorithm which is based on an orientation-sensitive probability measure. By incorporating...
Preparation and structure studies of crystalline and amorphous Ni, Ni-Y and Ni-Y-AI films / (1997)
Diss. (Doktorgrades) -- Georg-August-Universität zu Göttingen, 1997.
Preparation and structure studies of crystalline and amorphous Ni, Ni-Y and Ni-Y-Al films / (1997)
Göttingen, University, Diss., 1997.
Image segmentation based on oscillatory correlation (1997)
We study image segmentation on the basis of locally excitatory globally inhibitory oscillator networks (LEGION), whereby the phases of oscillators encode the binding of pixels. We introduce a...
Image segmentation based on oscillatory correlation (1997)
We study image segmentation on the basis of locally excitatory globally inhibitory oscillator networks (LEGION), whereby the phases of oscillators encode the binding of pixels. We introduce a...
Image segmentation based on oscillatory correlation (1997)
We study image segmentation on the basis of locally excitatory globally inhibitory oscillator networks (LEGION), whereby the phases of oscillators encode the binding of pixels. We introduce a lateral...
And Budi Yuwono, Deliang Wang, Budi Yuwono
A neural model for temporal pattern generation is used and analyzed for training with multiple complex sequences in a sequential manner. The network exhibits some degree of interference when new...
Shannon Campbell And, Shannon Campbell, Deliang Wang
A network of Wilson-Cowan oscillators is constructed, and its emergent properties of synchronization and desynchronization are investigated by both computer simulation and formal analysis. The...
Temporal Generalization of Simple Recurrent Networks (1996)
Xiaomei Liu, Stanley C. Ahalt, DeLiang Wang, Stanley C. Ahalt
Simple recurrent networks have been widely used in temporal processing applications. In this study we investigate temporal geralization of simple recurrent networks, drawing comparisons between...
Segmentation of Medical Data Using Locally Excitatory Globally Inhibitory Oscillator Networks (1996)
Naeem Shareef, DeLiang Wang, Roni Yagel
Advances in imaging technology allow clinicians to view internal structures of the body in a non-invasive manner. Segmentation is an important step in most medical applications which use sampled...
Modelling the Perceptual Segregation of Double Vowels With a Network of Neural Oscillators (1996)
Guy J. Brown, Guy J. Brown, DeLiang Wang, Deliang Wang
The ability of listeners to identify two simultaneously presented vowels can be improved by introducing a difference in fundamental frequency (F0) between the vowels. We propose an explanation for...
Primitive Auditory Segregation Based On Oscillatory Correlation (1996)
Auditory scene analysis is critical for complex auditory processing. We study auditory segregation from the neural network perspective, and develop a framework for primitive auditory scene analysis....
Range Image Segmentation Using a LEGION Network (1996)
This paper presents a neural network approach for range image segmentation. We use a locally excitatory globally inhibitory oscillator network (LEGION) as the framework for range image segmentation....
Relaxation Oscillators with Time Delay Coupling (1996)
Shannon R. Campbell, DeLiang Wang
We study networks of relaxation oscillators coupled with time delay synapses. A pair of oscillators is analyzed and shown to attain loosely synchronous solutions for a wide range of initial...
Shannon Campbell, DeLiang Wang
A network of Wilson-Cowan oscillators is constructed, and its emergent properties of synchronization and desynchronization are investigated by both computer simulation and formal analysis. The...
Incremental Learning of Complex Temporal Patterns (1995)
A neural model for temporal pattern generation is used and analyzed for training with multiple complex sequences in a sequential manner. The network exhibits some degree of interference when new...
Neural networks for temporal order learning and stimulus specific habituation / (1991)
Thesis (Ph. D.)--University of Southern California, 1991.
An oscillatory correlation model of auditory streaming
We present a neurocomputational model for auditory streaming, which is a prominent phenomenon of auditory scene analysis. The proposed model represents auditory scene analysis by oscillatory...