國立虎尾科技大學 |

Automatic Music Transcription in the Deep Learning Era = Perspectives on Generative Neural Networks /

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Automatic Music Transcription in the Deep Learning Era/ Jong Wook Kim.
其他題名:	Perspectives on Generative Neural Networks /
作者:	Kim, Jong Wook,
面頁冊數:	1 electronic resource (181 pages)
附註:	Source: Dissertations Abstracts International, Volume: 81-09, Section: A.
Contained By:	Dissertations Abstracts International81-09A.
標題:	Information technology. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27736453
ISBN:	9781392853870

Automatic Music Transcription in the Deep Learning Era = Perspectives on Generative Neural Networks /
Kim, Jong Wook,

Automatic Music Transcription in the Deep Learning Era Perspectives on Generative Neural Networks / [electronic resource] :Jong Wook Kim. - 1 electronic resource (181 pages)

Source: Dissertations Abstracts International, Volume: 81-09, Section: A.

The problem of automatic music transcription (AMT) is considered by many researchers as the holy grail of the field, because of the notorious complexity and difficulty of the problem. Meanwhile, the current decade has seen an unprecedented surge of deep learning where neural network methods have achieved tremendous success in many machine learning tasks including AMT. The success of deep learning is largely enabled by the ever-increasing amount of available data and the innovation of GPU hardware, allowing a deep learning model to enjoy the increased capacity to process such scale of data. While having more data and higher capacity translates better performance in general, there still remains the question of how to design an AMT model that can effectively incorporate the inductive bias for the task and best utilize the increased capacity.This thesis hypothesizes that an effective way to address this question is through the use of generative neural networks.Starting with a simplified setup of monophonic transcription, we learn the effectiveness of convolutional representation and the roles of dataset choices in data-driven models for music analysis. In the subsequent chapters, we examine the applications of deep generative models in music analysis and synthesis tasks, by introducing a WaveNet-based music synthesis model that learns a multi-dimensional timbre representation and a music language model applied in an adversarial manner to improve a piano transcription model. Finally, we combine the analysis and synthesis methods to develop a multi-instrument polyphonic music transcription system. From these observations, we conclude that deep generative models can be used to improve AMT in many ways, and they will be a crucial component for further advancing AMT.

English

ISBN: 9781392853870Subjects--Topical Terms:

559429
Information technology.
Subjects--Index Terms:

Automatic music transcription

Automatic Music Transcription in the Deep Learning Era = Perspectives on Generative Neural Networks /
LDR:03247nam a22004093i 4500 001 1172823
005 20260622113212.5
006 m o d
007 cr|nu||||||||
008 260803s2020 miu||||||m |||||||eng d
020 $a 9781392853870
035 $a (MiAaPQD)AAI27736453
035 $a AAI27736453
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Kim, Jong Wook, $e author. $3 1503424
245 1 0 $a Automatic Music Transcription in the Deep Learning Era $c Jong Wook Kim. $b Perspectives on Generative Neural Networks / $h [electronic resource] :
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 1 electronic resource (181 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 81-09, Section: A.
500 $a Advisors: Bello, Juan Pablo Committee members: Rowe, Robert ; Humphrey, Eric J.
502 $b Ph.D. $c New York University $d 2020.
520 # $a The problem of automatic music transcription (AMT) is considered by many researchers as the holy grail of the field, because of the notorious complexity and difficulty of the problem. Meanwhile, the current decade has seen an unprecedented surge of deep learning where neural network methods have achieved tremendous success in many machine learning tasks including AMT. The success of deep learning is largely enabled by the ever-increasing amount of available data and the innovation of GPU hardware, allowing a deep learning model to enjoy the increased capacity to process such scale of data. While having more data and higher capacity translates better performance in general, there still remains the question of how to design an AMT model that can effectively incorporate the inductive bias for the task and best utilize the increased capacity.This thesis hypothesizes that an effective way to address this question is through the use of generative neural networks.Starting with a simplified setup of monophonic transcription, we learn the effectiveness of convolutional representation and the roles of dataset choices in data-driven models for music analysis. In the subsequent chapters, we examine the applications of deep generative models in music analysis and synthesis tasks, by introducing a WaveNet-based music synthesis model that learns a multi-dimensional timbre representation and a music language model applied in an adversarial manner to improve a piano transcription model. Finally, we combine the analysis and synthesis methods to develop a multi-instrument polyphonic music transcription system. From these observations, we conclude that deep generative models can be used to improve AMT in many ways, and they will be a crucial component for further advancing AMT.
546 $a English
590 $a School code: 0146
650 # 4 $a Information technology. $3 559429
650 # 4 $a Music. $3 649088
650 # 4 $a Artificial intelligence. $3 559380
653 # # $a Automatic music transcription
653 # # $a Deep learning era
653 # # $a Neural networks
690 $a 0800
690 $a 0489
690 $a 0413
710 2 # $a New York University. $b Music and Performing Arts Professions. $3 1180054
720 1 $a Bello, Juan Pablo $e degree supervisor.
773 0 # $t Dissertations Abstracts International $g 81-09A.
790 $a 0146
791 $a Ph.D.
792 $a 2020
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27736453