ICASSP 2011

442 papers

Top Research Directions

Research directions most represented by ICASSP 2011 papers.

Deterministic Equivalents for Large Wireless Systems 2
Semidefinite Relaxation for Non-Convex Engineering Optimization 2
Successive Convex Approximation for Nonconvex Optimization 2
Overcoming Idealized Assumptions in Channel Modeling 2
Joint Active and Passive Beamforming Optimization 2
The Perceptual Evaluation Gap in Generative Audio 2
Boundary and Center Biases in Change Point Detection 1
High Resolution Parametric Spectral Estimation 1
Detecting Multiple Sequential Shifts in Time Series 1
The Cosparse Analysis Model for Signal Recovery 1
Detecting Shifts in Multivariate Data Dependencies 1
Concentration Inequalities for High Dimensional Systems 1
Compression via Rate Distortion Optimization 1
Shift Invariance in Discrete Wavelet and Sparse Representations 1
Adaptive Sparse Estimation with Unknown Sparsity 1

Top Authors

AuthorPapers
Georgios B. Giannakis9
Alfred O. Hero8
Haizhou Li6
Shrikanth Narayanan6
Wing-Kin Ma6
Lin-shan Lee5
Rémi Gribonval5
Axel Roebel4
Bhiksha Raj4
Michael Elad4
Peter Ramadge4
Shinji Watanabe4
Dilek Hakkani Tur3
Eric Fosler-Lussier3
Gaël Richard3
Gonzalo Mateos3
Guillermo Sapiro3
Haris Vikalo3
Kong Aik Lee3
LINGYU DUAN3

Impactful Papers

Papers from ICASSP 2011 that shaped research clusters.

Foundational

Influential

Papers

Title
Structured discriminative models for noise robust continuous speech recognition.
Structured Output Layer neural network language model
Subspace pursuit method for kernel-log-linear models
Superpixel-based object class segmentation using conditional random fields
Switching linear dynamic transducer for stereo data based speech feature mapping
Synthesizing visual speech trajectory with minimum generation error
Target localization with NLOS circularly reflected AOAS
Template-based methods for sentence generation and speech synthesis
Temporal hysteresis model of time varying subjective video quality
Temporal recurrence hashing algorithm for mining commercials from multimedia streams
The compressive multiplexer for multi-channel compressive sensing
The grouped two-sided orthogonal Procrustes problem
The HKCUPU system for the NIST 2010 speaker recognition evaluation
The IBM 2009 GALE Arabic speech transcription system
The least-mean-magnitude-phase algorithm with applications to communications systems
The meaning of interior tomography
The MIT LL 2010 speaker recognition evaluation system: Scalable language-independent speaker recognition
The Rotational Lasso
The SRI NIST 2010 speaker recognition evaluation system
Time-evolving modeling of social networks
Time-frequency reassigned features for automatic chord recognition
Time-frequency segmentation of bird song in noisy acoustic environments
Time-varying lung ventilation analysis of 4DCT using image registration
Towards improving network flow watermarks using the repeat-accumulate codes
Towards reduced false-alarms using cohorts
Toward text message normalization: Modeling abbreviation generation
Tracking changes in continuous emotion states using body language and prosodic cues
Tracking performance of adaptively biased adaptive filters
Trading off communications bandwidth with accuracy in adaptive diffusion networks
Trajectory triangulation: 3D motion reconstruction with ℓ1 optimization
Transient acoustic signal classification using joint sparse representation
Unsupervised extraction of audio-visual objects
User verification: Matching the uploaders of videos across accounts
USPACOR: Universal sparsity-controlling outlier rejection
Variational approximation of long-span language models for lvcsr
Video aesthetic quality assessment by combining semantically independent and dependent features
Video anomaly recovery from compressed spectral imaging
Weighted and structured sparse total least-squares for perturbed compressive sampling
Weighted compressed sensing and rank minimization
When codeword frequency meets geographical location
When to add another dimension when communicating over MIMO channels
Why word error rate is not a good metric for speech recognizer training for the speech translation task?

« prev Page 9/9