KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Author: search.filters.author.Chivapreecha, SorawatSubject: search.filters.subject.convolutional neural network

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Musical Key Classification Using Convolutional Neural Network Based on Extended Constant-Q Chromagram
    (2022-01-01)
    Chivapreecha, Sorawat
    ;
    Sinjanakhom, Tantep
    ;
    Trirat, Akraphon
    In the field of music information retrieval, musical key classification is one of the challenges. This paper illustrates the advantages of the proposed system with relevant experimental results, starting with diverse audio datasets for feature extraction used for training and testing a classification model which is based on a convolutional neural network (CNN). The goal is to develop a feature that can improve the neural network's performance. To compare the effect of input features on efficiency, a basic CNN is trained from the ground up and utilized as an image classification tool. The Chromagram-24, an augmented version of the input chroma feature, is proposed to improve the accuracy of musical key detection. In terms of weighted score, the model using Chromagram-24 as an input feature outperforms the model trained using a conventional 12-dimensional chromagram by 12.77% and achieves the highest score of 85.63% when classifying full-length songs. Chromagrams are generated using audio excerpts ranging in length from 15 to 60 seconds for local key estimation, whereas, for global key estimation, a full-length audio set is used. The results indicate that, given the different lengths of training audio input, executing the model using a chromagram of a 60-second audio excerpt yields the best results.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    A Deep Learning Approach to Digital Filter Parameter Estimation Based on Amplitude Responses
    (2021-01-21)
    Yospanya, Poonna
    ;
    Chivapreecha, Sorawat
    ;
    Jongsataporn, Thitaphan
    This paper presents our attempt to tackle the problem of digital filter type and parameter estimation given a set of points sampled from a filter frequency response. We compared results from various multilayer perceptron and convolutional neural network configurations. The results suggest that a convolutional neural network generally produces faster convergence with a lower loss at the same number of epochs than a multilayer perceptron network. However, the maximum amplitude response error, which is the true performance metrics, can be comparable in some cases. A combination of multiple best-performing configurations for different tasks is used to assemble the final model.