Speaker recognition approach can be categorized into speaker identification and speaker verification. These two subfields have a bit varied in definition from domain usage. If we has a voice input, the goal of speaker verification is for authentication by determining an answer from a question: "is the voice someone's voice?" For speaker identification, will try to find an answer: "the voice is whose voice?" It can be thought that verification is a special case of open-set identification. In this work, deep learning model using a convolution neural network (CNN) for speaker identification is proposed. The voice input to the method is no constrained on the words the speaker speaks. That means it is in a form of text-independent of which more difficult than text-dependent system. By the method, each 2 seconds of the speaker voice is transform to a spectrogram image and input to the generated CNN model training from scratch. The proposed CNN based method is compared to the classic Mel-frequency cepstral coefficients (MFCCs) based featured extraction method classified by support vector machine (SVM). Where, up to date, MFCC is the most popular feature extracted method for audio and speech signal. Our proposed method that the spectrogram image is used as an input is also compared to a case when image of raw signal wave is employed to the CNN model. Experiments are conducted on the speech from five speakers speak in Thai language of which voices are extracted from YouTube. It reveals the proposed CNN based method trains on spectrogram image of voice is the best compared to the other two methods. The average classification results of the testing set by the proposed method is 95.83%. For MFCC based method is 91.26% and for CNN model trained on image of raw signal wave is only 49.77%. The proposed method is very efficient when only short utterance of voice is used as an input.Index Terms-Convolution neural network (CNN), deep learning, speaker recognition, speaker identification, text-independent.
Various sub-tasks on modern construction management system require automatic or semi-automatic processes in handling the operation inside. Especially for construction progress monitoring task, the automatic process in classifying the difference of each construction material from an image is necessary in the preliminary stage. The more the preciseness in automatic classifying, the more the exactness in assessment of each material had been used. Subsequently, the progress of the construction can be evaluated with the highest degree of reliability. As a result, classification of construction material images is very essential process for automatic progress monitoring. Whereas, the similarities in material image appearances are the major classifying challenges. All most all existing related works have been studied based on hand-designed features of which the classified accuracy still not much appreciated from different studied datasets. In our work, automatic feature extracted method from the prominent technique in deep learning, convolution neural network (CNN), is proposed. The pre-trained CNN architectures of AlexNet and GoogleNet are adopt with the task of construction material images classification in the concept of transfer learning. Both of fixed feature extractor and fine-tuning schemes of transfer learning are technically implemented and evaluated. Analyzing results from the two pre-trained architectures expose very impressive and interesting circumstances to the studied dataset. Entirely, fine-tuning scheme of GoogleNet reveals the highest classification result by 95.50 percent of accuracy. Index Terms-Convolution neural network (CNN), deep learning, transfer learning, construction material, image classification.
Skin cancer is one of the most common human malignancies. It is a kind of skin diseases caused by abnormal growth of skin cells. Clinically, dermatological disease including skin cancer can be divided into many types. Treatment options for each type are varying depending on the prognosis of a disease. Type of skin disease or dermatological classification is an initial process of clinical screening. Traditional method of initial clinical screening requires a visual diagnosing by specialized expertise. In case the disease is classified as a type of skin cancers, it is a serious case of dermatological disease that should be treated promptly. Therefore, an automatic approach applied for this classification task is very useful. In this work, we propose an automatic method for skin disease classification using deep learning model of convolution neural network, or CNN. In order to increase the classification performance of CNN, we employ both image data and background knowledge of the patient in the modeling process. The experimental results performed on a public dataset show that the CNN model can classify skin diseases with 79.29% accuracy, while our proposed method to incorporate background knowledge of patient in the modeling phase can improve the accuracy up to 80.39%.
Abstract-This research proposes time series forecasting of commodity prices by using multiresolution analysis from wavelet transform. In this work, discrete wavelet transform based multiresolution decomposition of Deubechies family is used. Firstly, Deubechies wavelet transform is applied to the training set of time series data up to level four. The reconstruction values of the approximation part of wavelet from each level are then used for the forecasting process by ARIMA model. The validation set of data is used to analyze and select the best model from all 4 levels of multiresolution decomposition. Finally, best selected validating model is used for evaluating the remaining testing data set. The forecasting results by using multiresolution analysis are compared to the case where the original data are directly modeled and forecasted by ARIMA. Results based on the mean absolute percentage error evaluation from using multiresolution analysis are better for both of the two studied data including daily gold price and rubber price. By applying multiresolution analysis, the improvement is 10.83% for gold price and 42.68% for rubber price. The variances of errors from the proposed method on both data sets are also much less than directly use the original time series data for forecasting.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.