ICASSP 2015

459 papers

Top Research Directions

Research directions most represented by ICASSP 2015 papers.

Contrastive Estimation for Unnormalized Probability Models 2
Asymptotic Network Independence in Decentralized Optimization 2
Dynamic Sparsity Adaptation for Signal Recovery 2
Distributed Optimization over Directed Networks 2
Signal Recovery Beyond the Gaussian Measurement Assumption 2
Momentum and Inertia for Accelerated Optimization 2
Overcoming Ambiguity in Electrophysiological Source Localization 2
Parallelizing Recurrent Models via Linear State Transitions 2
The Vocabulary Scaling Bottleneck in Language Models 2
Sparse Signal Recovery from Underdetermined Measurements 2
Optimizing Non-Convex and Non-Smooth Sparsity Constraints 2
Stationary Point Convergence in Nonconvex Optimization 2
Solving Complex Optimization via Network Flow Reductions 1
Learning from Implicit Feedback in Conversational Systems 1
Eliminating Topological Bias in Directed Decentralized Networks 1

Top Authors

AuthorPapers
Alfred O. Hero10
Haizhou Li7
Shrikanth Narayanan5
Yuantao Gu5
EngSiong Chng4
Kong Aik Lee4
Mingyi Hong4
Nancy F. Chen4
Philip Schniter4
Sergios Theodoridis4
Sharon Gannot4
Timo Gerkmann4
Alexander Bertrand3
Axel Roebel3
Babak Hassibi3
Bin Ma3
Enrico Magli3
Florent Krzakala3
Florian Metze3
Georgios B. Giannakis3

Impactful Papers

Papers from ICASSP 2015 that shaped research clusters.

Foundational

Influential

Papers

Title
Source-specific informative prior for i-vector extraction
Sparse HMM-based speech enhancement method for stationary and non-stationary noise environments
Sparse null space basis pursuit and analysis dictionary learning for high-dimensional data analysis
Sparse representation for frequency warping based voice conversion
Sparse sensing for distributed gaussian detection
Sparse symbol detection by a greedy tree search
Sparsity aware minimum error entropy algorithms
Sparsity pattern recovery using FRI methods
Speaker adaptive training for deep neural networks embedding linear transformation networks
Spectral conversion using deep neural networks trained with multi-source speakers
Spectral properties of neuronal pulse interval modulation
Spectrum cartography using quantized observations
Speech acoustic modeling from raw multichannel waveforms
Speech dereverberation using a learned speech model
Speech emotion recognition with acoustic and lexical features
Speech recognition with prediction-adaptation-correction recurrent neural networks
Speech Separation based on signal-noise-dependent deep neural networks for robust speech recognition
Spikes from compound action potentials in simulated microelectrode recordings
Stability and continuity of centrality measures in weighted graphs
Structural segmentation of Hindustani concert audio with posterior features
Structure discovery of deep neural network based on evolutionary algorithms
Structured sparse signal models and decomposition algorithm for super-resolution in sound field recording and reproduction
Subspace learning using consensus on the grassmannian manifold
Subspace projection matrix completion on Grassmann manifold
Super-resolution in Phase Space
Support knowledge-aided sparse Bayesian learning for compressed sensing
The AMG1608 dataset for music emotion recognition
The efficiency of view synthesis prediction for 3D video coding: A spectral domain analysis
The intrinsic value of HFO features as a biomarker of epileptic activity
The proportional mean decomposition: A bridge between the Gaussian and bernoulli ensembles
The role of glottal source parameters for high-quality transformation of perceptual age
The THUEE system for the openKWS14 keyword search evaluation
The widely linear quaternion recursive total least squares
Tokenizing fundamental frequency variation for Mandarin tone error detection
Total Jensen divergences: Definition, properties and clustering
Towards machines that know when they do not know: Summary of work done at 2014 Frederick Jelinek Memorial Workshop
Transmission distortion modeling for view synthesis prediction based 3-D video streaming
Trinicon-BSS system incorporating robust dual beamformers for noise reduction
Twice-universal piecewise linear regression via infinite depth context trees
Unicode-based graphemic systems for limited resource languages.
Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis
Unsupervised data selection and word-morph mixed language model for tamil low-resource keyword search
Unsupervised detection of malware in persistent web traffic
Unsupervised feature learning for urban sound classification
Unsupervised learning of acoustic features via deep canonical correlation analysis
Unsupervised neural network based feature extraction using weak top-down constraints
Unusual event detection in crowded scenes by trajectory analysis
Utilizing spectro-temporal correlations for an improved speech presence probability based noise power estimation
Variational Bayes learning of multiscale graphical models
Visual and acoustic identification of bird species

« prev Page 9/10 next »