Isolated guitar transcription using a deep belief network

Burlet, Gregory; Hindle, Abram

doi:10.7717/peerj-cs.109

Cited by 6 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The isolated data island has arisen due to data privacy issues that have received high attention ( Yang et al, 2021a , 2021b ). The isolated data island can lead to less data being collected, yet machine learning models need more data for training in order to achieve excellent accuracy ( Burlet & Hindle, 2017 ; Baumer, 2018 ; Wang et al, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

OES-Fed: a federated learning framework in vehicular network based on noise data filtering

Lei

Wang

Caiyu

et al. 2022

PeerJ Computer Science

View full text Add to dashboard Cite

The Internet of Vehicles (IoV) is an interactive network providing intelligent traffic management, intelligent dynamic information service, and intelligent vehicle control to running vehicles. One of the main problems in the IoV is the reluctance of vehicles to share local data resulting in the cloud server not being able to acquire a sufficient amount of data to build accurate machine learning (ML) models. In addition, communication efficiency and ML model accuracy in the IoV are affected by noise data caused by violent shaking and obscuration of in-vehicle cameras. Therefore we propose a new Outlier Detection and Exponential Smoothing federated learning (OES-Fed) framework to overcome these problems. More specifically, we filter the noise data of the local ML model in the IoV from the current perspective and historical perspective. The noise data filtering is implemented by combining data outlier, K-means, Kalman filter and exponential smoothing algorithms. The experimental results of the three datasets show that the OES-Fed framework proposed in this article achieved higher accuracy, lower loss, and better area under the curve (AUC). The OES-Fed framework we propose can better filter noise data, providing an important domain reference for starting field of federated learning in the IoV.

show abstract

Section: Introductionmentioning

confidence: 99%

OES-Fed: a federated learning framework in vehicular network based on noise data filtering

Lei

Wang

Caiyu

et al. 2022

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…Other works perform classification, e.g. [4], which uses a collection of hand-crafted features to estimate, among other parameters, the string associated with each note, or [12], where a Deep Belief Network (DBN) is utilized to produce pitch and polyphony estimates. Bayesian classification has also been proposed [6,13,14] to estimate the string and fret of notes.…”

Section: Introductionmentioning

confidence: 99%

A Data-Driven Methodology for Considering Feasibility and Pairwise Likelihood in Deep Learning Based Guitar Tablature Transcription Systems

Cwitkowitz¹,

Driedger²,

Duan³

2022

Preprint

View full text Add to dashboard Cite

Guitar tablature transcription is an important but understudied problem within the field of music information retrieval. Traditional signal processing approaches offer only limited performance on the task, and there is little acoustic data with transcription labels for training machine learning models. However, guitar transcription labels alone are more widely available in the form of tablature, which is commonly shared among guitarists online. In this work, a collection of symbolic tablature is leveraged to estimate the pairwise likelihood of notes on the guitar. The output layer of a baseline tablature transcription model is reformulated, such that an inhibition loss can be incorporated to discourage the co-activation of unlikely note pairs. This naturally enforces playability constraints for guitar, and yields tablature which is more consistent with the symbolic data used to estimate pairwise likelihoods. With this methodology, we show that symbolic tablature can be used to shape the distribution of a tablature transcription model's predictions, even when little acoustic data is available. † Main work completed as a research intern at Chordify. Copyright: © 2022 Frank Cwitkowitz et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. 1 https://www.ultimate-guitar.com/ 2 Examples include bends, slides, hammer-ons/offs, vibrato, etc.

show abstract

“…These algorithm parameters are used in the experiments detailed in the following sections.The experiments conducted in this paper were run on a machine with an Intel R Core TM i7 3.07 GHz quad core CPU, 24 GB of RAM, and an Nvidia GeForce GTX 970 GPU with 1664 CUDA cores. For more details regarding these preliminary experiments, consult the thesis ofBurlet (2015).…”

mentioning

confidence: 99%

Peer Review #1 of "Isolated guitar transcription using a deep belief network (v0.2)"

Humphrey¹

2017

View full text Add to dashboard Cite

Music transcription involves the transformation of an audio recording to common music notation, colloquially referred to as sheet music. Manually transcribing audio recordings is a difficult and time-consuming process, even for experienced musicians. In response, several algorithms have been proposed to automatically analyze and transcribe the notes sounding in an audio recording; however, these algorithms are often general-purpose, attempting to process any number of instruments producing any number of notes sounding simultaneously. This paper presents a polyphonic transcription algorithm that is constrained to processing the audio output of a single instrument, specifically an acoustic guitar. The transcription system consists of a novel note pitch estimation algorithm that uses a deep belief network and multi-label learning techniques to generate multiple pitch estimates for each analysis frame of the input audio signal. Using a compiled dataset of synthesized guitar recordings for evaluation, the algorithm described in this work results in an 11% increase in the f-measure of note transcriptions relative to Zhou et al.'s transcription algorithm in the literature. This paper demonstrates the effectiveness of deep, multi-label learning for the task of polyphonic transcription.

show abstract

Isolated guitar transcription using a deep belief network

Cited by 6 publications

References 24 publications

OES-Fed: a federated learning framework in vehicular network based on noise data filtering

OES-Fed: a federated learning framework in vehicular network based on noise data filtering

A Data-Driven Methodology for Considering Feasibility and Pairwise Likelihood in Deep Learning Based Guitar Tablature Transcription Systems

Peer Review #1 of "Isolated guitar transcription using a deep belief network (v0.2)"

Contact Info

Product

Resources

About