Topic
Dynamic time warping
About: Dynamic time warping is a research topic. Over the lifetime, 6013 publications have been published within this topic receiving 133130 citations.
Papers published on a yearly basis
Papers
More filters
24 Aug 2007
TL;DR: A hybrid of hidden Markov models (HMMs) and artificial neural network (ANN) has been proposed to classify emotions, combining advantage on capability to dynamic time warping of HMM and pattern recognition of ANN.
Abstract: Speech emotion recognition, as a vital part of affective human computer interaction, has become a new challenge to speech processing. In this paper, a hybrid of hidden Markov models (HMMs) and artificial neural network (ANN) has been proposed to classify emotions, combining advantage on capability to dynamic time warping of HMM and pattern recognition of ANN. HMMs, which export likelihood probabilities and optimal state sequences, have been used to model speech feature sequences, while ANN has been employed to make a decision. The recognition result of the hybrid classification has been compared with the isolated HMMs by two speech corpora, Germany database and Mandarin database, and the average recognition rates have reached 83.8% and 81.6% respectively.
36 citations
•
13 Aug 2014
TL;DR: In this article, a gesture recognition method based on an acceleration sensor was proposed, which comprises the following steps: automatically collecting gesture acceleration data, preprocessing, calculating the similarity of all gesture sample data so as to obtain a similarity matrix, extracting a gesture template, constructing a gesture dictionary by utilizing the gesture template and carrying out sparse reconstruction and gesture classification.
Abstract: The invention discloses a gesture recognition method based on an acceleration sensor. The gesture recognition method based on an acceleration sensor comprises the following steps: automatically collecting gesture acceleration data, preprocessing, calculating the similarity of all gesture sample data so as to obtain a similarity matrix, extracting a gesture template, constructing a gesture dictionary by utilizing the gesture template, and carrying out sparse reconstruction and gesture classification on the gesture sample data to be recognized by adopting an MSAMP (modified sparsity algorithm adaptive matching pursuit) algorithm. According to the invention, the compressed sensing technique and a traditional DTW (dynamic time warping) algorithm are combined, and the adaptability of the gesture recognition to different gesture habits is improved, and by adopting multiple preprocessing methods, the practicability of the gesture recognition method is improved. Additionally, the invention also discloses an automatic collecting algorithm of the gesture acceleration data; the additional operation of traditional gesture collection is eliminated; the user experience is improved; according to the invention, a special sensor is not required, the gesture recognition method based on the acceleration sensor can be used for terminals carried with the acceleration sensor; the hardware adaptability is favorable, and the practicability of the recognition method is enhanced. The coordinate system is uniform, and can be adaptive to different multiple gesture habits.
36 citations
••
TL;DR: A generalized action retrieval framework is introduced, which achieves fully unsupervised, robust, and actor-independent action search in large-scale database and an appearance hashing strategy is presented to address the performance degeneration caused by divergent actor appearances.
36 citations
•
01 Jan 2018TL;DR: This paper introduces FastWWSearch: an efficient and exact method to learn WW, which shows on 86 datasets that the method is always faster than the state of the art, with at least one order of magnitude and up to 1000x speed-up.
Abstract: Time series classification maps time series to labels. The nearest neighbor algorithm (NN) using the Dynamic Time Warping (DTW) similarity measure is a leading algorithm for this task and a component of the current best ensemble classifiers for time series. However, NN-DTW is only a winning combination when its meta-parameter – its warping window – is learned from the training data. The warping window (WW) intuitively controls the amount of distortion allowed when comparing a pair of time series. With a training database of N time series of lengths L, a naive approach to learning the WW requires Θ(N·L) operations. This often results in NN-DTW requiring days for training on datasets containing a few thousand time series only. In this paper, we introduce FastWWSearch: an efficient and exact method to learn WW. We show on 86 datasets that our method is always faster than the state of the art, with at least one order of magnitude and up to 1000x speed-up.
36 citations
••
12 Nov 2012TL;DR: The proposed system is applied to a dataset Arabic sign language gestures and it yielded a recognition rates 92.5% and 95.1% for user dependent and user independent models respectively.
Abstract: This paper presents a low complexity classification approach for sign language recognition using sensor-based gloves. Each glove includes 5 bend sensors and a 3D accelerometer. The classification approach is based on a novel feature extraction method based on accumulated differences (ADs). The ADs approach projects the dynamics of the glove sensor readings into one feature vector. This vector is normally of high dimensionality as it is meant to capture the dynamics of a sign language gesture. As such, dimensionality reduction using stepwise regression is applied to feature vectors before classification. Thereafter, a simple minimum distance classifier is employed. The proposed system is applied to a dataset Arabic sign language gestures and it yielded a recognition rates 92.5% and 95.1% for user dependent and user independent models respectively. Moreover, the computational complexity of the proposed method is O(N) as compared to the classical approach of Dynamic Time Warping (DTW) which is of O(N2) complexity.
36 citations