ICASSP 2018

703 papers

Top Research Directions

Research directions most represented by ICASSP 2018 papers.

Adversarial Spectral Refinement for High-Fidelity Audio Synthesis 3
Cross-Task Generalization in Audio and Speech Processing 3
Semidefinite Relaxation for Non-Convex Engineering Optimization 3
Parallelizing Recurrent Models via Linear State Transitions 3
Balancing Noise Suppression and Speech Distortion 3
Feature Learning Directly from Raw Audio Waveforms 3
Learning Fine-Grained Audio Timestamps from Coarse Tags 3
Robust Audio Modeling Under Acoustic Domain Shift 3
Estimating the Bayes Error Rate from Data 2
Dimension-Free Convergence Rates for Optimal Transport 2
Sub-Nyquist Spatial Field Reconstruction via Sparse Recovery 2
External Language Model Integration for Neural Speech Recognition 2
Blind Source Separation for Correlated Signals 2
Grapheme Based Acoustic Modeling for Lexicon Free Speech 2
Alternating Optimization for Blind Image Deconvolution 2

Top Authors

AuthorPapers
Georgios B. Giannakis8
Wenwu Wang8
Yanmin Qian8
Jinyu Li7
Zhifeng Chen7
Bo Li6
Florian Metze6
Keisuke Kinoshita6
Patrick Nguyen6
Rohit Prabhavalkar6
Yonghui Wu6
Alfred O. Hero5
Chung-Cheng Chiu5
Hung-yi Lee5
Kai Yu5
Mark A. Hasegawa-Johnson5
YONG XU5
Alejandro Ribeiro4
Alexandre Gramfort4
Anand D. Sarwate4

Impactful Papers

Papers from ICASSP 2018 that shaped research clusters.

Foundational

Influential

Papers

Title
Deep Learning Based Speech Beamforming
Deep Learning for Accelerated Ultrasound Imaging
Deep Learning for Joint Source-Channel Coding of Text
Deep Residual Learning for Small-Footprint Keyword Spotting
Deep Stock Representation Learning: From Candlestick Charts to Investment Decisions
Deeptongue: Tongue Segmentation Via Resnet
Deep Transfer Learning for EEG-Based Brain Computer Interface
Deep Uniqueness-Aware Hashing for Fine-Grained Multi-Label Image Retrieval
Deep Word Embeddings for Visual Speech Recognition
Defending Against Packet-Size Side-Channel Attacks in Iot Networks
Deformation Stability of Deep Convolutional Neural Networks on Sobolev Spaces
Demixing and Blind Deconvolution of Graph-Diffused Sparse Signals
Demystifying Deep Learning: a Geometric Approach to Iterative Projections
Densely Connected Progressive Learning for LSTM-Based Speech Enhancement
Dense Multimodal Fusion for Hierarchically Joint Representation
Depth Super-Resolution Using Joint Adaptive Weighted Least Squares And Patching Gradient
Depth Super-Resolution with Deep Edge-Inference Network and Edge-Guided Depth Filling
Designing an Effective Metric Learning Pipeline for Speaker Diarization
Developing a Geometric Deformable Model for Radar Shape Inversion
Developing Far-Field Speaker System Via Teacher-Student Learning
Diabetic Retinopathy Detection Based on Deep Convolutional Neural Networks
Dictionary Learning for High Dimensional Graph Signals
Differentially Private Distributed Principal Component Analysis
Digraph Fourier Transform via Spectral Dispersion Minimization
Direct Ensemble Estimation of Density Functionals
Directly Solving the Original Ratiocut Problem for Effective Data Clustering
Discriminative Probabilistic Framework for Generalized Multi-Instance Learning
Distributed Analytical Graph Identification
Distributed Coupled Learning Over Adaptive Networks
Distributed Diffusion Adaptation Over Graph Signals
Distributed Estimation Under Network Model Uncertainty
Distributed Solution of Large-Scale Linear Systems Via Accelerated Projection-Based Consensus
DNN-Based Concurrent Speakers Detector and its Application to Speaker Extraction with LCMV Beamforming
DNN Based Speaker Embedding Using Content Information for Text-Dependent Speaker Verification
Document Quality Estimation Using Spatial Frequency Response
Domain Adversarial Training for Accented Speech Recognition
Domain and Speaker Adaptation for Cortana Speech Recognition
Domain Attentive Fusion for End-to-end Dialect Identification with Unknown Target Domain
Domain Independent Key Term Extraction from Spoken Content Based on Context and Term Location Information in the Utterances
Dpca: Dimensionality Reduction for Discriminative Analytics of Multiple Large-Scale Datasets.
Driver Estimation in Non-Linear Autoregressive Models
Dual-Channel Modulation Energy Metric for Direct-to-Reverberation Ratio Estimation
Dual Frequency- and Block-Permutation Alignment for Deep Learning Based Block-Online Blind Source Separation
Dynamic Frame Skipping for Fast Speech Recognition in Recurrent Neural Network Based Acoustic Models
Dynamic Matrix Recovery from Partially Observed and Erroneous Measurements
Dynamic Multi-Rater Gaussian Mixture Regression Incorporating Temporal Dependencies of Emotion Uncertainty Using Kalman Filters
Edge-Aware Context Encoder for Image Inpainting
Eeg-Based Video Identification Using Graph Signal Modeling and Graph Convolutional Neural Network
Effective Attention Mechanism in Dynamic Models for Speech Emotion Recognition
Effects of Lombard Reflex on the Performance of Deep-learning-based Audio-visual Speech Enhancement Systems

« prev Page 5/15 next »