**dtw**241

[1807.08666] ASR-free CNN-DTW keyword spotting using multilingual bottleneck features for almost zero-resource languages

12 weeks ago by arsyed

We consider multilingual bottleneck features (BNFs) for nearly zero-resource keyword spotting. This forms part of a United Nations effort using keyword spotting to support humanitarian relief programmes in parts of Africa where languages are severely under-resourced. We use 1920 isolated keywords (40 types, 34 minutes) as exemplars for dynamic time warping (DTW) template matching, which is performed on a much larger body of untranscribed speech. These DTW costs are used as targets for a convolutional neural network (CNN) keyword spotter, giving a much faster system than direct DTW. Here we consider how available data from well-resourced languages can improve this CNN-DTW approach. We show that multilingual BNFs trained on ten languages improve the area under the ROC curve of a CNN-DTW system by 10.9% absolute relative to the MFCC baseline. By combining low-resource DTW-based supervision with information from well-resourced languages, CNN-DTW is a competitive option for low-resource keyword spotting.

dtw
neural-net
convnet
asr
kws
12 weeks ago by arsyed

Twitter

december 2017 by vielmetti

RT @DTWeetin: The snow is causing delays and cancellations at #DTW. Remember to check with your airline before heading to the air…

DTW
from twitter_favs
december 2017 by vielmetti

Twitter

december 2017 by vielmetti

At #EWR where @United cancelled my #EWR to #DTW flight, conveniently just a few minutes after I checked my bag.

R…

EWR
DTW
from twitter
R…

december 2017 by vielmetti

[1705.05681] Optimal Warping Paths are unique for almost every pair of Time Series

may 2017 by arsyed

"An optimal warping path between two time series is generally not unique. The size and form of the set of pairs of time series with non-unique optimal warping path is unknown. This article shows that optimal warping paths are unique for almost every pair of time series in a measure-theoretic sense. All pairs of time series with non-unique optimal warping path form a negligible set and are geometrically the union of zero sets of quadratic forms. The result is useful for analyzing and understanding adaptive learning methods in dynamic time warping spaces."

papers
time-series
alignment
dtw
may 2017 by arsyed

[1703.01141] Dynamic State Warping

may 2017 by arsyed

"The ubiquity of sequences in many domains enhances significant recent interest in sequence learning, for which a basic problem is how to measure the distance between sequences. Dynamic time warping (DTW) aligns two sequences by nonlinear local warping and returns a distance value. DTW shows superior ability in many applications, e.g. video, image, etc. However, in DTW, two points are paired essentially based on point-to-point Euclidean distance (ED) without considering the autocorrelation of sequences. Thus, points with different semantic meanings, e.g. peaks and valleys, may be matched providing their coordinate values are similar. As a result, DTW is sensitive to noise and poorly interpretable. This paper proposes an efficient and flexible sequence alignment algorithm, dynamic state warping (DSW). DSW converts each time point into a latent state, which endows point-wise autocorrelation information. Alignment is performed by using the state sequences. Thus DSW is able to yield alignment that is semantically more interpretable than that of DTW. Using one nearest neighbor classifier, DSW shows significant improvement on classification accuracy in comparison to ED (70/85 wins) and DTW (74/85 wins). We also empirically demonstrate that DSW is more robust and scales better to long sequences than ED and DTW."

papers
time-series
sequence
alignment
dtw
may 2017 by arsyed

Twitter

march 2017 by peterhoneyman

Dinner is a @Bigalora capricciosa pizza and a glass of Montepulciano at #DTW. Headed to Miami Beach w/…

DTW
from twitter
march 2017 by peterhoneyman

[1703.01541] Soft-DTW: a Differentiable Loss Function for Time-Series

march 2017 by arsyed

"We propose in this paper a differentiable learning loss between time series. Our proposal builds upon the celebrated Dynamic Time Warping (DTW) discrepancy. Unlike the Euclidean distance, DTW is able to compare asynchronous time series of varying size and is robust to elastic transformations in time. To be robust to such invariances, DTW computes a minimal cost alignment between time series using dynamic programming. Our work takes advantage of a smoothed formulation of DTW, called soft-DTW, that computes the soft-minimum of all alignment costs. We show in this paper that soft-DTW is a differentiable loss function, and that both its value and its gradient can be computed with quadratic time/space complexity (DTW has quadratic time and linear space complexity). We show that our regularization is particularly well suited to average and cluster time series under the DTW geometry, a task for which our proposal significantly outperforms existing baselines (Petitjean et al., 2011). Next, we propose to tune the parameters of a machine that outputs time series by minimizing its fit with ground-truth labels in a soft-DTW sense."

papers
time-series
dtw
march 2017 by arsyed

**related tags**

Copy this bookmark: