2024-03-29T10:27:04Z
https://jcaa.caa-aca.ca/index.php/jcaa/oai
oai:jcaa.caa-aca.ca:article/2617
2014-01-31T01:15:21Z
jcaa:ART-SIG
nmb a2200000Iu 4500
"130601 2013 eng "
2291-1391
0711-6659
dc
Sound objects: a bio-inspired representation, hierarchical sparse to very large dimensions used in recognition
Brodeur, Simon
Rouat, Jean
The emphasis is put on the hierarchical structure, independence and sparseness aspects of auditory signalrepresentations in high-dimensional spaces, so as to define the components of auditory objects. The conceptof an auditory object and its neural representation is introduced. An illustrative application then follows,consisting in the analysis of various auditory signals : speech, music and natural outdoor environments. Anew automatic speech recognition (ASR) system is then proposed and compared to a conventional statisticalsystem. The proposed system clearly shows that an object-based analysis introduces a great flexibility androbustness for the task of speech recognition. The integration of knowledge from neuroscience and acousticsignal processing brings new ways of thinking to the field of classification of acoustic signals.
Canadian Acoustical Association / Association canadienne d'acoustique
2013-11-18 11:10:27
application/pdf
https://jcaa.caa-aca.ca/index.php/jcaa/article/view/2617
Canadian Acoustics; Vol. 41 No. 2 (2013)
eng
Copyright (c)
oai:jcaa.caa-aca.ca:article/3941
2023-09-12T03:21:19Z
jcaa:ART-SIG
nmb a2200000Iu 4500
"230824 2023 eng "
2291-1391
0711-6659
dc
Comparison of Various Algorithms: Research on Piano Audio Signal Feature Identification
Hao, Shuang
Hebei University of Science and Technology https://orcid.org/0009-0002-8203-1339
Accurate identification of piano audio signals helps in piano learning and composition. This article briefly introduced feature extraction methods for piano audio signals and three algorithms, dynamic time warping (DTW), back-propagation (BP), and convolutional neural network (CNN), which can recognize piano audio features. The three recognition algorithms were compared in the subsequent simulation experiments. It was found that for some single-note and multi-note piano audios, the recognition results of the CNN algorithm were consistent with the standard results, the BP algorithm had some differences, and the DTW algorithm had the most differences. As the number of notes in the piano audio increased, the recognition accuracy of all the algorithms decreased, but the CNN algorithm decreased the least, and its recognition performance was highest under the same number of notes, followed by the BP algorithm, and the DTW algorithm was the lowest.
Canadian Acoustical Association / Association canadienne d'acoustique
2023-08-24 00:00:00
application/pdf
https://jcaa.caa-aca.ca/index.php/jcaa/article/view/3941
Canadian Acoustics; Vol. 51 No. 2 (2023)
eng
Copyright (c) 2023 Shuang Hao