An HMM-Like Dynamic Time Warping Scheme for Automatic Speech Recognition

Abstract

In the past, the kernel of automatic speech recognition (ASR) is dynamic time warping (DTW), which is feature-based template matching and belongs to the category technique of dynamic programming (DP). Although DTW is an early developed ASR technique, DTW has been popular in lots of applications. DTW is playing an important role for the known Kinect-based gesture recognition application now. This paper proposed an intelligent speech recognition system using an improved DTW approach for multimedia and home automation services. The improved DTW presented in this work, called HMM-like DTW, is essentially a hidden Markov model- (HMM-) like method where the concept of the typical HMM statistical model is brought into the design of DTW. The developed HMM-like DTW method, transforming feature-based DTW recognition into model-based DTW recognition, will be able to behave as the HMM recognition technique and therefore proposed HMM-like DTW with the HMM-like recognition model will have the capability to further perform model adaptation (also known as speaker adaptation). A series of experimental results in home automation-based multimedia access service environments demonstrated the superiority and effectiveness of the developed smart speech recognition system by HMM-like DTW.

A Data-Driven Modeling Strategy for Smart Grid Power Quality Coupling Assessment Based on Time Series Pattern Matching

“…distance are used to implement the pattern matching on the UPQTS of voltage deviation [15,16]. The assessment results of of voltage deviation among the nodes are given in Figure 7.…”

“…The required time series pattern matching method should be applicable for the pattern feature matrices with the same row and different column numbers. DTW distance supports time stretching and warping, which can determine the alignment matching relation between two univariate time series [16]. Thus, this study proposes a FDP method based on DTW distance to implement the pattern matching on both UPQTS and MPQTS in different pollution patterns.…”

“…Common pattern matching methods for univariate time series are Euclidean distance (ED) and dynamic time warping (DTW) distance. ED is applicable for sample sequences of equal length [15], and DTW distance supports time stretching and warping [16]. However, the two methods consider only the data value difference and ignore the data variation characteristic, which may cause misjudgment in the pattern matching of univariate time series.…”

Three-layered hierarchical scheme with a Kinect sensor microphone array for audio-based human behavior recognition

“…In addition, two GMMs, detailed in Section 3, describing vocal and nonvocal acoustic events are established. Given the acoustic nature of this study, GMM is a more appropriate statistical model than the hidden Markov model is for describing an acoustic event [16,17]; the HMM is especially employed in speech recognition.…”

An eigenspace-based method with a user adaptation scheme for human gesture recognition by using Kinect 3D data

“…The developed approach, called Eigen3Dgesture, involves using PCA to derive significant eigen3Dgestures possessing the most critical information from Kinect 3D data. In addition, to enhance the proposed approach and the performance of the constructed eigenspace of Kinect 3D data, a user adaptation (UA) scheme [17], [18], which entails employing the active gesture data of a test user to adjust the eigenspace of Kinect 3D data such that the Eigen3Dgesture recognition model is more representative of a new test user, was developed in this study. Studies regarding the use of adaptation schemes in HMM-based and DTW-based Kinect gesture recognition systems are extremely rare.…”