Sorry, you need to enable JavaScript to visit this website.

Document Search

Achieving Centimeter-level Accuracy for Indoor Localization: A Time-Reversal Approach on WiFi Platforms
“UpatrasECE” SPCUP 2016 Project Report
Matlab Program for Wireless Powered Two Way Relay Channel (ICASSP 2016)
Information on the MAST ENF Power Signature Dataset
Linearly Augmented Deep Neural Network
Low-rank Matrix Recovery via Entropy Function
High-Resolution Sinusoidal Modeling of Unvoiced Speech
Performance Analysis for Pilot-based 1-bit Channel Estimation with Unknown Quantization Threshold
EXPLOITING LSTM STRUCTURE IN DEEP NEURAL NETWORKS FOR SPEECH RECOGNITION
Parallelizing WFST Speech Decoders (Poster)
The intrinsic value of HFO features as a biomarker of epileptic activity
Language Model Adaptation for ASR of Spoken Translations Using Phrase-based Translation Models and Named Entity Models
RECURRENT NEURAL NETWORKS FOR POLYPHONIC SOUND EVENT DETECTION IN REAL LIFE RECORDINGS
Recurrent neural networks for polyphonic sound event detection in real life recordings
Particle filters with independent resampling
Feature-Enrich Matrix Factorization for SLU at ICASSP16
Poster for Unsupervised User Intent Modeling by Feature-Enriched Matrix Factorization
CDSSM for Zero-Shot Intent Modeling at ICASSP16
Poster for Zero-Shot Learning of Intent Embeddings for Expansion by Convolutional Deep Structured Semantic Models
CLASSIFICATION OF BISYLLABIC LEXICAL STRESS PATTERNS IN DISORDERED SPEECH USING DEEP LEARNING
Examples of subband filters learned using ConvRBM: (a) filters in time-domain (i.e., impulse responses), (b) filters in frequency-domain (i.e., frequency responses).
FILTERBANK LEARNING USING CONVOLUTIONAL RESTRICTED BOLTZMANN MACHINE FOR SPEECH RECOGNITION
Examples of subband filters learned using ConvRBM: (a) filters in time-domain (i.e., impulse responses), (b) filters in frequency-domain (i.e., frequency responses).
FILTERBANK LEARNING USING CONVOLUTIONAL RESTRICTED BOLTZMANN MACHINE FOR SPEECH RECOGNITION
Poster for Beyond Low Rank + Sparse: Multi-scale Low Rank Matrix Decomposition

Pages