ICASSP 2017

593 papers

Top Research Directions

Research directions most represented by ICASSP 2017 papers.

Learning Latent Graph Topologies Directly from Data 3
Non-Negative Matrix Factorization for Spectrogram Decomposition 3
Convolutive Blind Source Separation in Reverberant Environments 3
Reconstructing Bandlimited Signals on Graphs 2
Robust Audio-Visual Speech Processing Under Visual Occlusion 2
Signal Recovery Beyond the Gaussian Measurement Assumption 2
Continuous Relaxations for Non-Convex Graph Optimization 2
Spectral Analysis of Directed Graphs 2
Joint Optimization of Speech Enhancement and Recognition 2
Cascading Errors in Hierarchical Architectures 2
Variational Inference as an Optimization Problem 2
Phase Retrieval from Intensity Measurements 2
Hybrid Convolutional Recurrent Networks for Audio Processing 2
Underdetermined Source Separation via Structural and Statistical Priors 2
Deterministic Cyclic Schedules in Iterative Optimization 1

Top Authors

AuthorPapers
Alfred O. Hero9
Alejandro Ribeiro7
Gaël Richard6
Shrikanth Narayanan6
Georgios B. Giannakis5
Keisuke Kinoshita5
Qingmin Liao5
Vince D. Calhoun5
Wenwu Wang5
Xuelong Li5
Yi-Hsuan Yang5
Zhong-Qiu Wang5
Anthony Man-Cho So4
Antonio G. Marques4
Aryan Mokhtari4
Babak Hassibi4
Gesualdo Scutari4
Mark D Plumbley4
Ruimin Hu4
Santiago Segarra4

Impactful Papers

Papers from ICASSP 2017 that shaped research clusters.

Foundational

Influential

Papers

Title
Surrounding adaptive tone mapping in displayed images under ambient light
Synchronization for multi-perspective videos in the wild
Taichi distance for person re-identification
Target detecton and tracking via structured convex optimization
Temporal localization of audio events for conflict monitoring in social media
Tensor-based crowdsourced clustering via triangle queries
The counterintuitive mechanism of graph-based semi-supervised learning in the big data regime
The geometry of random paired comparisons
The group k-support norm for learning with structured sparsity
The microsoft 2016 conversational speech recognition system
The Power-Oja method for decentralized subspace estimation/tracking
Time reversal based wireless events detection
Topic identification of spoken documents using unsupervised acoustic unit discovery
Topology inference of directed graphs using nonlinear structural vector autoregressive models
Towards a definition of local stationarity for graph signals
Towards stationary time-vertex signal processing
Towards the characterization of singing styles in world music
Towards wireless acoustic sensor networks for location estimation and counting of multiple speakers in real-life conditions
Traffic congestion analysis: A new Perspective
Traffic engineering for backhaul networks with wireless link scheduling
Trainable frontend for robust and far-field keyword spotting
Training algorithm to deceive Anti-Spoofing Verification for DNN-based speech synthesis
Training data reduction in deep neural networks with partial mutual information based feature selection and correlation matching based active learning
Transferring clothing parsing from fashion dataset to surveillance
Two-dimensional anti-jamming communication based on deep reinforcement learning
Two models for fusion of medical imaging data: Comparison and connections
Two-stage facial age prediction using group-specific features
Ultra-fast robust compressive sensing based on memristor crossbars
Unifying attribute splitting criteria of decision trees by Tsallis entropy
Universal bounds for the sampling of graph signals
Unsupervised speaker adaptation of batch normalized acoustic models for robust ASR
Unsupervised utterance-wise beamformer estimation with speech recognition-level criterion
Uplink and downlink user pairing in full-duplex multi-user systems: Complexity and algorithms
Using optimal transport for estimating inharmonic pitch signals
Using regional saliency for speech emotion recognition
Very deep convolutional networks for end-to-end speech recognition
Visual features for context-aware speech recognition
Wavelet-based single image super-resolution with an overall enhancement procedure
Weak law of large numbers for stationary graph processes
Weakly-supervised audio event detection using event-specific Gaussian filters and fully convolutional networks
When sparsity meets low-rankness: Transform learning with non-local low-rank constraint for image restoration
Why Do Neural Dialog Systems Generate Short and Meaningless Replies? a Comparison between Dialog and Translation
Xampling-enabled coexistence in spectrally crowded environments

« prev Page 12/12