ICASSP 2003

284 papers

Top Research Directions

Research directions most represented by ICASSP 2003 papers.

Optimizing Mother Wavelet Selection for Deep Learning 1
Translation Invariant Wavelet Transforms 1
Numerical Drift in Incremental and Recursive Updates 1
Multi-Factor Sentence Ranking for Extractive Summarization 1
Shift Invariance in Discrete Wavelet and Sparse Representations 1
Confidence Estimation for Robust Spoken Language Processing 1
Syntactic Tree Pruning for Sentence Compression 1
Decoupling Content Selection From Text Generation 1
Efficient Subspace Decomposition for Real-Time Signal Processing 1
Incremental Matrix Inversion via Rank One Updates 1
Syntactic Parsing of Spontaneous Speech Disfluencies 1

Top Authors

AuthorPapers
Jiri Navratil7
Georgios B. Giannakis6
Deniz Erdogmus5
Ahmet Murat Tekalp4
Ananthram Swami4
Chang D. Yoo4
Hiroshi Sawada3
Konstantinos N. Plataniotis3
Lihua Xie3
Luciana Ferrer3
Michael Unser3
Phil Woodland3
Rama Chellappa3
Shiguang Shan3
Wolfgang Utschick3
Aggelos Katsaggelos2
Alfred O. Hero2
Amit Roy-Chowdhury2
Arnaud Doucet2
Arthur Gretton2

Impactful Papers

Papers from ICASSP 2003 that shaped research clusters.

Foundational

Influential

Papers

Title
Speech enhancement based on the general transfer function GSC and postfiltering
Speech recognition using voice-characteristic-dependent acoustic models
Speech segmentation without speech recognition
Sphere-constrained ML detection for frequency-selective channels
Split-lexicon based hierarchical recognition of speech using syllable and word level acoustic units
Statistical shape theory for activity modeling
Stereoscopic panoramic video generation using centro-circular projection technique
Stochastic modeling of motion tracking failures
Subband parameter optimization of microphone arrays for speech recognition in reverberant environments
Surface plenoptic function: a tool for the sampling analysis of image-based rendering
Temporal registration of video sequences
The IBM system for the NIST-2002 cellular speaker verification evaluation
The incorporation of masking threshold to subspace speech enhancement
The kernel mutual information
The robustness of an almost-parsing language model given errorful training data
The SuperSID project: exploiting high-level information for high-accuracy speaker recognition
The VTP test for transients of equal detectability
Throughput maximization for the multiuser MIMO broadcast channel
Towards automatic transcription of large spoken archives - English ASR for the MALACH project
Tracking noise via dynamical systems with a continuum of states
Training a prosody-based dialog act tagger from unlabeled data
Transient behavior of affine projection algorithms
Triphone model reconstruction for Mandarin pronunciation variations
UBM-based real-time speaker segmentation for broadcasting news
Ultra-wideband communications: an idea whose time has come
Unsupervised clustering based reduced support vector machines
Using prosodic and conversational features for high-performance speaker recognition: report from JHU WS'02
Variational inference and learning for segmental switching state space models of hidden speech dynamics
Vector quantization techniques for GMM based speaker verification
Video synthesis of arbitrary views for approximately planar scenes
Virtual face image generation for illumination and pose insensitive face recognition
Wavelet video coding via a spatially adaptive lifting structure
Why take notes? Use the whiteboard capture system
Word level confidence measurement using semantic features

« prev Page 6/6