Dynamic Time Warping

79 papers with code • 0 benchmarks • 0 datasets

This task has no description! Would you like to contribute one?

Libraries

Use these libraries to find Dynamic Time Warping models and implementations

Most implemented papers

Soft-DTW: a Differentiable Loss Function for Time-Series

mblondel/soft-dtw ICML 2017

We propose in this paper a differentiable learning loss between time series, building upon the celebrated dynamic time warping (DTW) discrepancy.

Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models

vincent-leguen/STDL NeurIPS 2019

We introduce a differentiable loss function suitable for training deep neural nets, and provide a custom back-prop implementation for speeding up optimization.

Learning the Beauty in Songs: Neural Singing Voice Beautifier

moonintheriver/neuralsvb ACL 2022

Furthermore, we propose a latent-mapping algorithm in the latent space to convert the amateur vocal tone to the professional one.

A user-driven case-based reasoning tool for infilling missing values in daily mean river flow records

erin-list/gapit Environmental Modelling & Software 2006

In this work, we introduce gapIt, a user-driven case-based reasoning tool for infilling gaps in daily mean river flow records.

Multi-Scale Convolutional Neural Networks for Time Series Classification

zdcuob/Fully-Convlutional-Neural-Networks-for-state-of-the-art-time-series-classification- 22 Mar 2016

These methods are ad-hoc and separate the feature extraction part with the classification part, which limits their accuracy performance.

shapeDTW: shape Dynamic Time Warping

jiapingz/shapeDTW 6 Jun 2016

Dynamic Time Warping (DTW) is an algorithm to align temporal sequences with possible local non-linear distortions, and has been widely applied to audio, video and graphics data alignments.

Times series averaging and denoising from a probabilistic perspective on time-elastic kernels

pfmarteau/eKATS 28 Nov 2016

In the light of regularized dynamic time warping kernels, this paper re-considers the concept of time elastic centroid for a setof time series.

TimeNet: Pre-trained deep recurrent neural network for time series classification

kirarenctaon/timenet 23 Jun 2017

Inspired by the tremendous success of deep Convolutional Neural Networks as generic feature extractors for images, we propose TimeNet: a deep recurrent neural network (RNN) trained on diverse time series in an unsupervised manner using sequence to sequence (seq2seq) models to extract features from time series.

Data augmentation using synthetic data for time series classification with deep residual networks

hfawaz/aaltd18 7 Aug 2018

This is surprising as the accuracy of deep learning models for TSC could potentially be improved, especially for small datasets that exhibit overfitting, when a data augmentation method is adopted.

Multimodal One-Shot Learning of Speech and Images

rpeloff/multimodal-one-shot-learning 9 Nov 2018

Imagine a robot is shown new concepts visually together with spoken tags, e. g. "milk", "eggs", "butter".