ICASSP 2005

329 papers

Top Research Directions

Research directions most represented by ICASSP 2005 papers.

The Misalignment of Variance and Relevance in Dimensionality Reduction 2
Supervised Dimensionality Reduction 2
Combating the Curse of Dimensionality via Subspace Learning 2
How Signal to Noise Ratio Governs Spatial Correlation 1
Quantifying Rare Events in Stochastic Systems 1
Numerical Drift in Incremental and Recursive Updates 1
Large Deviation Error Exponents for Statistical Inference 1
Explicit Duration Modeling with Semi-Markov Processes 1
The Vulnerabilities of External API Dependencies 1
Out of Sample Extension for Manifold Learning 1
Inductive Extensions for Spectral and Manifold Learning 1
Scaling Silent and Visual Speech to Large Vocabularies 1
Interpolated Language Models for Domain Adaptation 1
Overcoming Idealized Assumptions in Channel Modeling 1
Incremental Matrix Inversion via Rank One Updates 1

Top Authors

AuthorPapers
Alfred O. Hero17
Ahmet Murat Tekalp5
Ananthram Swami5
Deniz Erdogmus5
Georgios B. Giannakis5
Rama Chellappa5
Brian M. Sadler4
Min Wu4
Philip Schniter4
Phil Woodland4
Brian Kingsbury3
Dongxiao Zhu3
Hiroshi Sawada3
Jeff Bilmes3
Kai Yu3
Mari Ostendorf3
Ramani Duraiswami3
Rémi Gribonval3
Shih-Fu Chang3
S Kevin Zhou3

Impactful Papers

Papers from ICASSP 2005 that shaped research clusters.

Foundational

Influential

Papers

Title
The energy efficiency of on-off keying with partial CSI and peak power constraints
The finer directional wavelet transform [image processing applications]
The IBM 2004 Conversational Telephony System for Rich Transcription
The Laplacian spectral classifier
The manifolds of spatial hearing
The modified CUSUM algorithm for slow and drastic change detection in general HMMs with unknown change parameters
The variational EM algorithm for on-line identification of extended AR models [speech processing example]
Throughput and energy efficiency of sensor networks with multiuser receivers and spatial diversity
Time and energy efficient Viterbi decoding using FPGAs
Time delay estimation via multichannel cross-correlation [audio signal processing applications]
Tonotopic Multi-Layered Perceptron: A Neural Network for Learning Long-Term Temporal Features for Speech Recognition
Towards a unified framework for content-based audio analysis
Tracking Algorithm Using Background-Foreground Motion Models and Multiple Cues
Training LVCSR Systems on Thousands of Hours of Data
Training Wideband Acoustic Models using Mixed-Bandwidth Training Data via Feature Bandwidth Extension
Translation Insensitive Image Similarity in Complex Wavelet Domain
Two kinds of timing cues and their usage in concept detection in news video
Understanding the topology of a telephone network via internally-sensed network tomography
Unsupervised auditory scene categorization via key audio effects and information-theoretic co-clustering
Unsupervised classification via decision trees: an information-theoretic perspective
Using Local & Global Phonotactic Features in Chinese Dialect Identification
Vector form EM and suboptimal joint state and parameter estimation
Video assisted speech source separation
Video Background Retrieval using Mosaic Images
Video coding with motion-compensated temporal transforms and side information
Voice Activity Detection based on Generalized Gamma Distribution
Web-Data Augmented Language Models for Mandarin Conversational Speech Recognition
Wiener Filtering for Generalized Error Resilient Time Domain Lapped Transform
Yet another subspace tracker

« prev Page 7/7