ICASSP 2004

318 papers

Top Research Directions

Research directions most represented by ICASSP 2004 papers.

Constrained Coding for DNA Storage and Synthesis 1
Resolving Front-Back Ambiguity in Acoustic Localization 1
Direct Minimization of Classification Error 1
Scaling Noisy Data for Better Generalization 1
Adaptive Thresholding for Dynamic Anomaly Detection 1
Joint Latent State and Parameter Estimation 1
Aligning Sound Sources Across Frequency Bins 1
Bootstrapping Speech Tasks with Pretrained Acoustic Models 1
Speech Transformation Without Parallel Training Data 1
Adapting Language Models to Temporal Drift 1
Convolutive Blind Source Separation in Reverberant Environments 1
Robust Audio Modeling Under Acoustic Domain Shift 1

Top Authors

AuthorPapers
Alfred O. Hero8
Georgios B. Giannakis5
Hiroshi Sawada5
Rama Chellappa5
Ananthram Swami4
Deniz Erdogmus4
Phil Woodland4
Wing-Kin Ma4
Brian M. Sadler3
Jeff Bilmes3
Konstantinos N. Plataniotis3
Lawrence K. Saul3
Ramani Duraiswami3
Samy Bengio3
Shoko Araki3
S Kevin Zhou3
Alan Wee-Chung Liew2
Alper Tunga Erdogan2
Christian Fuegen2
Dilek Hakkani Tur2

Impactful Papers

Papers from ICASSP 2004 that shaped research clusters.

Foundational

Influential

Papers

Title
Content-based music similarity search and emotion detection
Contraction, smoothness, and low-pass filtering
Convolutive blind source separation for more than two sources in the frequency domain
Cooperative diversity through virtual arrays in multihop networks
Corrective language modeling for large vocabulary ASR with the perceptron algorithm
Cross-lingual latent semantic analysis for language modeling
Cryptographically secure identity certificates
Custom arithmetic for high-speed, low-resource ASR systems
DBN based multi-stream models for audio-visual speech recognition
Decentralized source localization and tracking [wireless sensor networks]
Design of fully-diverse multi-antenna codes based on Sp(2)
Detecting the presence of an inhomogeneous region in a homogeneous background: taking advantages of the underlying geometry via manifolds
Development of the 2003 CU-HTK conversational telephone speech transcription system
Differential space-time modulation with transmit-beamforming for correlated MIMO fading channels
Dimensionality reduction using MCE-optimized LDA transformation
Directional hypercomplex wavelets for multidimensional signal analysis and processing
Direction-of-arrival estimation of wideband sources using arbitrary shaped multidimensional arrays
Dirichlet-based probability model applied to human skin detection [image skin detection]
Discriminative training for speaker identification based on maximum model distance algorithm
Distributed maximum likelihood estimation for sensor networks
Distributed maximum likelihood estimation for sensor networks.
Distributed space-time coding strategies for wideband multihop networks: regenerative vs. non-regenerative relays
DNA-based matching of digital signals
Effect of MAC design on source estimation in dense sensor networks
Efficient and robust distributed speech recognition (DSR) over wireless fading channels: 2D-DCT compression, iterative bit allocation, short BCH code and interleaving
Efficient motion tracking using gait analysis
Efficient (piecewise) linear minmax approximation of digital signals
Efficient statistical pruning for maximum likelihood decoding
Efficient VLSI implementation of inverse discrete cosine transform [image coding applications]
Embedded speech recognition system on 8-bit MCU core
Energy-aware secure multicast communication in ad-hoc networks using geographic location information
English-Chinese bilingual text-independent speaker verification
Enhanced standard compliant distributed speech recognition (Aurora encoder) using rate allocation
Error protection of video over wireless local area networks through real-time retry limit adaptation
Estimation of short-term predictor parameters for coding and enhancement of noisy speech
Evaluating average causal effect using wireless sensor networks
Exploratory analysis and visualization of speech and music by locally linear embedding
Extending boosting for call classification using word confusion networks
Face relighting for face recognition under generic illumination
Fast blind equalization method based on subgradient projections
Fast initialization of particle filters using a modified metropolis-Hastings algorithm: mode-hungry approach
Fine-granular-scalability video streaming over wireless LANs using cross layer error control
Fixed fragment-size packet transmissions with distributed redundancy over multipath fading channels
Flexible layout and optimal cancellation of the orthonormality error for spherical microphone arrays
Formant tracking by mixture state particle filter
Fractional Fourier transform features for speech recognition
Frequency synchronization in OFDM
FSF subspace-based algorithm for joint DOA-FOA estimation
Fusion based speech segmentation in DARPA SPINE2 task
Fusion of gait and face for human identification

« prev Page 3/7 next »