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
The PyTorch-Kaldi Speech Recognition Toolkit
Time-Frequency Masking-Based Speech Enhancement Using Generative Adversarial Network
Time-Frequency Networks for Audio Super-Resolution
Tomography of Adaptive Multi-Agent Networks Under Limited Observation
Tone Reservation and Solvability Concepts for the Papr Problem in General Orthonormal Transmission Systems
To Reverse the Gradient or Not: An Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognition
Towards Adaptive Deep Brain Stimulation in Parkinson'S Disease: Lfp-Based Feature Analysis and Classification
Towards a Wearable Cough Detector Based on Neural Networks
Towards Complete Polyphonic Music Transcription: Integrating Multi-Pitch Detection and Rhythm Quantization
Towards Directly Modeling Raw Speech Signal for Speaker Verification Using CNNS
Toward Secure Image Denoising: A Machine Learning Based Realization
Towards End-to-end Spoken Language Understanding
Towards Language-Universal End-to-End Speech Recognition
Towards Learning Nuisance-Free Representations of Speech
Towards Open Set Camera Model Identification Using a Deep Learning Framework
Towards Predicting Physiology from Speech During Stressful Conversations: Heart Rate and Respiratory Sinus Arrhythmia
Tracked Instance Search
Training Deep Neural Networks via Optimization Over Graphs
Training Probabilistic Spiking Neural Networks with First- To-Spike Decoding
Transcribing Lyrics from Commercial Song Audio: the First Step Towards Singing Content Processing
Transferable Positive/Negative Speech Emotion Recognition via Class-wise Adversarial Domain Adaptation
Transferring Information Between Neural Networks
True Gradient-Based Training of Deep Binary Activated Neural Networks Via Continuous Binarization
Twitter User Geolocation Using Deep Multiview Learning
Two-Dimensional Quaternion Sparse Principle Component Analysis
Two-Sample Testing can be as Hard as Structure Learning in Ising Models: Minimax Lower Bounds
U-Fresh: An Fri-Based Single Image Super Resolution Algorithm and An Application in Image Compression
Unbiased Distance Based Non-Local Fuzzy Means
Understanding Deep Neural Networks through Input Uncertainties
Understanding Recurrent Neural State Using Memory Signatures
Understanding The Aesthetic Styles of Social Images
Underwater Optical Sensor Networks Localization with Limited Connectivity
Unequal Error Protection Querying Policies for the Noisy 20 Questions Problem
Unifying Probabilistic Models for Time-Frequency Analysis.
Unlimited Sampling of Sparse Signals
Unsupervised Cross-Corpus Speech Emotion Recognition Using Domain-Adaptive Subspace Learning
Unsupervised Discovery of an Extended Phoneme Set in L2 English Speech for Mispronunciation Detection and Diagnosis
Unsupervised Domain Adaptation via Domain Adversarial Training for Speaker Recognition
Unsupervised Learning of Semantic Audio Representations
Using Accelerometric and Gyroscopic Data to Improve Blood Pressure Prediction from Pulse Transit Time Using Recurrent Neural Network
Using Optimal Mass Transport for Tracking and Interpolation of Toeplitz Covariance Matrices
Variational Deep Learning for Low-Dose Computed Tomography
Vision as an Interlingua: Learning Multilingual Semantic Embeddings of Untranscribed Speech
Visual-Only Recognition of Normal, Whispered and Silent Speech
Voice Impersonation Using Generative Adversarial Networks
WaveGlow: A Flow-based Generative Network for Speech Synthesis
Wavelet Shrinkage and Thresholding Based Robust Classification for Brain-Computer Interface
Wavenet Based Low Rate Speech Coding
Weighted and Multi-Task Loss for Rare Audio Event Detection
West: Word Encoded Sequence Transducers.

« prev Page 14/15 next »