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
TL;DR: This research seeks to compare each phoneme recognition results from warping factor between 0.74 and 1.54 with 0.02 increments on nine different ranges of frequency warping boundary to analyse the best setting for the highest recognition performance.
Abstract: The overall success of automatic speech recognition (ASR) depends on efficient phoneme recognition performance and quality of speech signal received in ASR. However, dissimilar inputs of speakers affect the overall recognition performance. One of the main problems that affect recognition performance is inter-speaker variability. Vocal tract length normalization (VTLN) is introduced to compensate inter-speaker variation on the speaker signal by applying speaker-specific warping of the frequency scale of a filter bank. Instead of measuring the performance on word level with speaker-specific warping, this research focuses on direct tackling at the phoneme level and applying VTLN on all speakers’ speech signals to analyse the best setting for the highest recognition performance. This research seeks to compare each phoneme recognition results from warping factor between 0.74 and 1.54 with 0.02 increments on nine different ranges of frequency warping boundary. The warp factor and frequency warping range...
46 citations
TL;DR: This paper describes these networks as a way for learning feature extractors by constrained back-propagation and shows such a time-delay network to be capable of dealing with a near real-sized problem: French digit recognition.
46 citations
18 Sep 2011
TL;DR: A continuous left to right HMM for each symbol class is designed and four online local features are used, including a new feature: normalized distance to stroke edge, to get initialization of the Gaussian Mixture Models' parameters.
Abstract: This paper presents a recognition system based on Hidden Markov Model (HMM) for isolated online handwritten mathematical symbols. We design a continuous left to right HMM for each symbol class and use four online local features, including a new feature: normalized distance to stroke edge. A variant of segmental K-means is used to get initialization of the Gaussian Mixture Models' parameters which represent the observation probability distribution of the HMMs. The system obtains top-1 recognition rate of 82.9% and top-5 recognition rate of 97.8% on a dataset containing 20281 training samples and 2202 testing samples of 93 classes of symbols. For multi-stroke symbols, the top-1 recognition rate is 74.7% and the top-5 recognition rate is 95.5%. For single-stroke symbols, the top-1 recognition rate is 86.8% and the top-5 recognition rate is 98.9%. (MacLean et al., 2010) applied dynamic time warping algorithm on all the 70 classes of single-stroke symbols. Their top-1 recognition rate is 85.8%, and top-5 recognition rate is 97.0%. Our system gets top-1 recognition rate of 85.5% and top-5 recognition rate of 99.1% on the same 70 classes of single-stroke symbols.
46 citations
Posted Content•
TL;DR: This work defines the normalized Dynamic Time Warping (nDTW) metric, which is naturally sensitive to the order of the nodes composing each path, is suited for both continuous and graph-based evaluations, and can be efficiently calculated, and defines SDTW, which constrains nDTW to only successful paths.
Abstract: In instruction conditioned navigation, agents interpret natural language and their surroundings to navigate through an environment. Datasets for studying this task typically contain pairs of these instructions and reference trajectories. Yet, most evaluation metrics used thus far fail to properly account for the latter, relying instead on insufficient similarity comparisons. We address fundamental flaws in previously used metrics and show how Dynamic Time Warping (DTW), a long known method of measuring similarity between two time series, can be used for evaluation of navigation agents. For such, we define the normalized Dynamic Time Warping (nDTW) metric, that softly penalizes deviations from the reference path, is naturally sensitive to the order of the nodes composing each path, is suited for both continuous and graph-based evaluations, and can be efficiently calculated. Further, we define SDTW, which constrains nDTW to only successful paths. We collect human similarity judgments for simulated paths and find nDTW correlates better with human rankings than all other metrics. We also demonstrate that using nDTW as a reward signal for Reinforcement Learning navigation agents improves their performance on both the Room-to-Room (R2R) and Room-for-Room (R4R) datasets. The R4R results in particular highlight the superiority of SDTW over previous success-constrained metrics.
46 citations
23 Sep 2007
TL;DR: This paper describes character based elastic matching using local features for recognizing online handwritten data using Dynamic time warping with four different feature sets containing x-y, normalized first and second derivatives and curvature features and proposed a 2-stage recognition scheme.
Abstract: This paper describes character based elastic matching using local features for recognizing online handwritten data. Dynamic time warping (DTW) has been used with four different feature sets: x-y features, shape context (SC) and tangent angle (TA) features, generalized shape context feature (GSC) and the fourth set containing x-y, normalized first and second derivatives and curvature features. Nearest neighborhood classifier with DTW distance was used as the classifier. In comparison, the SC and TA feature set was found to be the slowest and the fourth set was best among all in the recognition rate. The results have been compiled for the online handwritten Tamil and Telugu data. On Telugu data we obtained an accuracy of 90.6% with a speed of 0.166 symbols/sec. To increase the speed we have proposed a 2-stage recognition scheme using which we obtained accuracy of 89.77% but with a speed of 3.977 symbols/sec.
46 citations