moomou

(ノ≧∇≦)ノ ミ ┸┸

ML paper notes

Posted at — Sep 1, 2017

2017-09

LEARNING FINE-GRAINED IMAGE SIMILARITY WITH DEEP RANKING


DEEP METRIC LEARNING USING TRIPLET NETWORK

DISTILLING THE KNOWLEDGE IN A NEURAL NETWORK

Questions


REGULARIZING NEURAL NETWORKS BY PENALIZING CONFIDENT OUTPUT DISTRIBUTIONS

Questions


2017-08

VOCO: TEXT-BASED INSERTION AND REPLACEMENT IN AUDIO NARRATION

keywords: voice conversion, t2s

Question


AN OVERLAP-ADD TECHNIQUE BASED ON WAVEFORM SIMILARITY (WSOLA) FOR HIGH QUALITY TIME-SCALE MODIFICATION OF SPEECH

keywords: voice synthesis, text 2 speech

Questions


LEARNING A PREDICTABLE AND GENERATIVE VECTOR REPRESENTATION FOR OBJECTS


LEARNING TO COMPARE IMAGE PATCHES VIA CONVOLUTIONAL NEURAL NETWORKS

keyword: feature extraction

Questions


DATA-DRIVEN SYNTHESIS OF SMOKE FLOWS WITH CNN-BASED FEATURE DESCRIPTORS

keyword: low dimension feature descriptor

Questions


DEEP UNFOLDING: MODEL-BASED INSPIRATION OF NOVEL DEEP ARCHITECTURES

Questions


AUDIO-DRIVEN FACIAL ANIMATION BY JOINT END-TO-END LEARNING OF POSE AND EMOTION

keywords: e2e, audio, emotion, lip vertex position

Questions


ARCHITECTURES FOR DEEP NEURAL NETWORK BASED ACOUSTIC MODELS DEFINED OVER WINDOWED SPEECH WAVEFORMS

keywords: raw input

Questions


SPECTRAL SUBBAND CENTROID FEATURES FOR SPEECH RECOGNITION


LCN, CNN, DNN FOR TEXT DEPENDENT SV


Resnet

keywords: skip layer,


NETWORK IN A NETWORK

keywords: NIN


AUTOMATIC GAIN CONTROL AND MULTI-STYLE TRAINING FOR ROBUST SMALL-FOOTPRINT KEYWORD SPOTTING WITH DEEP NEURAL NETWORKS

keywords: multi-style training, small-footprint models


ACOUSTIC MODELLING FROM THE SIGNAL DOMAIN USING CNNS

keywords: CNN, raw waveform, statistic extraction layer, Network In Network nonlinearity


END-TO-END TEXT-DEPENDENT SPEAKER VERIFICATION

keywords: speaker verification, end-to-end training

Questions


DEEP NEURAL NETWORK-BASED SPEAKER EMBEDDINGS FOR END-TO-END SPEAKER VERIFICATION

keywords: speaker vr, text-indepdendent

Questions


2017-07

BOOSTED TREES

keywords: boosted trees, random trees


DEEP LEARNING FOR HATE SPEECH DETECTION IN TWEETS

keywords: glove, fasttext, hate speech, GBDT (gradient boosted decision trees)

Questions

A TIME DELAY NEURAL NETWORK ARCHITECTURE FOR EFFICIENT MODELING OF LONG TEMPORAL CONTEXTS

keywords: subsampling, dnn,

MAXOUT NETWORK SUMMARY


DEEP NEURAL NETWORKS FOR SMALL FOOTPRINT TEXT-DEPENDENT SPEAKER VERIFICATION


DEEP SPEAKER FEATURE LEARNING FOR TEXT-INDEPENDENT SPEAKER VERIFICATION

keywords: SR, speaker feature vector

Questions


A SIMPLE WAY TO INITIALIZE RECURRENT NETWORKS OF RECTIFIED LINEAR UNITS

keywords: identity matrix, rnn, lstm


MULTISCALE CONTEXT AGGREGATION BY DILATED CONVOLUTION

keywords: dilated, convolution, segmentation, dense prediction


DENOISING WITH WAVENT

keywords: noncausal dilated convolution, raw signal,


SQUEEZE NET

keywords: deep compression, small model


MULTI-SCALE CONTEXT AGGREGATION BY DILATED CONVOLUTIONS

keywords: dilated convolution, segmentation, dense prediction


2017-06

LAYER NORMALIZATION


ATTENTION IS ALL YOU NEED

keywords: transformer, self attention, multi-head attention, encoder-decoder

Questions

LABEL SMOOTHING