Behnam Faghih

The Acceptable Range of Pitch Frequencies And Duration of Notes in Singing

Annotated-VocalSet: A Singing Voice Dataset

Applied Sciences

There are insufficient datasets of singing files that are adequately annotated. One of the availa... more There are insufficient datasets of singing files that are adequately annotated. One of the available datasets that includes a variety of vocal techniques (n = 17) and several singers (m = 20) with several WAV files (p = 3560) is the VocalSet dataset. However, although several categories, including techniques, singers, tempo, and loudness, are in the dataset, they are not annotated. Therefore, this study aims to annotate VocalSet to make it a more powerful dataset for researchers. The annotations generated for the VocalSet audio files include fundamental frequency contour, note onset, note offset, the transition between notes, note F0, note duration, Midi pitch, and lyrics. This paper describes the generated dataset and explains our approaches to creating and testing the annotations. Moreover, four different methods to define the onset/offset are compared.

Download

Annotated-VocalSet: A Singing Voice Dataset

Applied Sciences, 2022

There are insufficient datasets of singing files that are adequately annotated. One of the availa... more There are insufficient datasets of singing files that are adequately annotated. One of the available datasets that includes a variety of vocal techniques (n = 17) and several singers (m = 20) with several WAV files (p = 3560) is the VocalSet dataset. However, although several categories, including techniques, singers, tempo, and loudness, are in the dataset, they are not annotated. Therefore, this study aims to annotate VocalSet to make it a more powerful dataset for researchers. The annotations generated for the VocalSet audio files include fundamental frequency contour, note onset, note offset, the transition between notes, note F0, note duration, Midi pitch, and lyrics. This paper describes the generated dataset and explains our approaches to creating and testing the annotations. Moreover, four different methods to define the onset/offset are compared.

A New Method for Detecting Onset and Offset for Singing in Real-Time and Offline Environments

Applied Sciences

This paper introduces a new method for detecting onsets, offsets, and transitions of the notes in... more This paper introduces a new method for detecting onsets, offsets, and transitions of the notes in real-time solo singing performances. It identifies the onsets and offsets by finding the transitions from one note to another by considering trajectory changes in the fundamental frequencies. The accuracy of our approach is compared with eight well-known algorithms. It was tested with two datasets that contained 130 files of singing. The total duration of the datasets was more than seven hours and had more than 41,000 onset annotations. The analysis metrics used include the Average, the F-Measure Score, and ANOVA. The proposed algorithm was observed to determine onsets and offsets more accurately than the other algorithms. Additionally, unlike the other algorithms, the proposed algorithm can detect the transitions between notes.

Download

Smart-Median: A New Real-Time Algorithm for Smoothing Singing Pitch Contours

Applied Sciences

Pitch detection is usually one of the fundamental steps in audio signal processing. However, it i... more Pitch detection is usually one of the fundamental steps in audio signal processing. However, it is common for pitch detectors to estimate a portion of the fundamental frequencies incorrectly, especially in real-time environments and when applied to singing. Therefore, the estimated pitch contour usually has errors. To remove these errors, a contour smoother algorithm should be employed. However, because none of the current contour-smoother algorithms has been explicitly designed to be applied to contours generated from singing, they are often unsuitable for this purpose. Therefore, this article aims to introduce a new smoother algorithm that rectifies this. The proposed smoother algorithm is compared with 15 other smoother algorithms over approximately 2700 pitch contours. Four metrics were used for the comparison. According to all the metrics, the proposed algorithm could smooth the contours more accurately than other algorithms. A distinct conclusion is that smoother algorithms sh...

Download

A New Method for Detecting Onset and Offset for Singing in Real-Time and Offline Environments

by Behnam Faghih and Sutirtha Chakraborty

Applied Sciences, 2022

This paper introduces a new method for detecting onsets, offsets, and transitions of the notes in... more This paper introduces a new method for detecting onsets, offsets, and transitions of the notes in real-time solo singing performances. It identifies the onsets and offsets by finding the transitions from one note to another by considering trajectory changes in the fundamental frequencies. The accuracy of our approach is compared with eight well-known algorithms. It was tested with two datasets that contained 130 files of singing. The total duration of the datasets was more than seven hours and had more than 41,000 onset annotations. The analysis metrics used include the Average, the F-Measure Score, and ANOVA. The proposed algorithm was observed to determine onsets and offsets more accurately than the other algorithms. Additionally, unlike the other algorithms, the proposed algorithm can detect the transitions between notes.

Smart-Median: A New Real-Time Algorithm for Smoothing Singing Pitch Contours

Applied Sciences, 2022

Pitch detection is usually one of the fundamental steps in audio signal processing. However, it i... more Pitch detection is usually one of the fundamental steps in audio signal processing. However, it is common for pitch detectors to estimate a portion of the fundamental frequencies incorrectly, especially in real-time environments and when applied to singing. Therefore, the estimated pitch contour usually has errors. To remove these errors, a contour smoother algorithm should be employed. However, because none of the current contour-smoother algorithms has been explicitly designed to be applied to contours generated from singing, they are often unsuitable for this purpose. Therefore, this article aims to introduce a new smoother algorithm that rectifies this. The proposed smoother algorithm is compared with 15 other smoother algorithms over approximately 2700 pitch contours. Four metrics were used for the comparison. According to all the metrics, the proposed algorithm could smooth the contours more accurately than other algorithms. A distinct conclusion is that smoother algorithms should be designed according to the contour type and the result’s final applications.

A Multi-Agent based Load balancing System in IaaS Cloud Environment

International Robotics & Automation Journal, 2016

Infrastructure as a service (IaaS) is a type of cloud computing in which a third-party provider h... more Infrastructure as a service (IaaS) is a type of cloud computing in which a third-party provider hosts virtualized computing resources over the Internet for executing tasks in the cloud computing. Whenever some VMs are overloaded and some VMs are under loaded, this situation may cause to SLA violation and leads to the reduction of customer satisfaction level and further affects the cloud provider leading to penalty. However, in this study, we propose a Multiple Agent-based Load Balancing Algorithm (MA) in which shift the load in the IaaS to achieve well dynamic load balancing across virtual machines for maximizing the utilization. The proposed algorithm with regard to changing environment and characteristics of the VMs, perform both of senderinitiated and receiver-initiated approach to balances the load of an IaaS in such a way that the amount of waiting time of the tasks in the queue is minimal and at the same time the SLA is guaranteed. We have compared the proposed algorithm with existing load balancing and scheduling algorithms via simulation. The simulation results show that the proposed algorithm is more effective and there is a good improvement in the load-balance, response time and makespan.

Download

Singing Blocks

Harmony and Chord progressions are the foundational architecture of a number of genres of Western... more Harmony and Chord progressions are the foundational architecture of a number of genres of Western music, from Classical, to Jazz, to popular music. For any musician, mastering the rules can be an important step in learning the skills of composition. The rules are difficult to learn, however. There have been efforts to create innovative educational software displays but to date Virtual Reality (VR) systems have not been investigated. The innately physical nature of VR creates an immersive experience that is impossible with other approaches. This work explains our concept of a VR educational game for young adult learners upwards of certain Western music genres. It draws subtle analogies to the architecture of harmony by presenting a number of levels in which the user builds chords and progressions. The aim is that they journey towards interacting creatively with the harmonics representation. Suggestions are also given as to how an effective evaluation procedure may be carried out in t...

Download

Considerations for the Next Generation of Singing Tutor Systems

Journal of The Audio Engineering Society, 2019

An investigation into several pitch detection algorithms for singing phrases analysis

2019 30th Irish Signals and Systems Conference (ISSC), 2019

This article provides an investigation into four different pitch detection algorithms: pYin, Praa... more This article provides an investigation into four different pitch detection algorithms: pYin, Praat, Phase Lock Loops (PLL)-based, and an Extended Complex Kalman Filter approach. The first two algorithms compute the pitch on a frame-by-frame basis while the latter two work on a sample-by-sample basis. Only in recent years has there been a noticeable increase in the number of papers applying pitch detection techniques to sung phrases. This investigation is done on a dataset contained 76 files of singers. To create a ground truth from the data an alternative approach using the Spear analysis program is applied. The algorithms are compared using a new Singing Data Analyser tool. It was observed that the pYin and Praat are the most reliable algorithms while the PLL and Kalman filter algorithms are very dependent on the user-selected parameters.

Singing-Blocks : Considerations for a Virtual Reality Game to create chords and progressions

Harmony and Chord progressions are the foundational architecture of a number of genres of Western... more Harmony and Chord progressions are the foundational architecture of a number of genres of Western music, from Classical, to Jazz, to popular music. For any musician, mastering the rules can be an important step in learning the skills of composition. The rules are difficult to learn, however. There have been efforts to create innovative educational software displays but to date Virtual Reality (VR) systems have not been investigated. The innately physical nature of VR creates an immersive experience that is impossible with other approaches. This work explains our concept of a VR educational game for young adult learners upwards of certain Western music genres. It draws subtle analogies to the architecture of harmony by presenting a number of levels in which the user builds chords and progressions. The aim is that they journey towards interacting creatively with the harmonics representation. Suggestions are also given as to how an effective evaluation procedure may be carried out in t...

Download

User Interface Design for E-Learning Software

User interface (UI) is point of interaction between user and computer software. The success and f... more User interface (UI) is point of interaction between user and computer software. The success and failure of a software application depends on User Interface Design (UID). Possibility of using a software, easily using and learning are issues influenced by UID. The UI is significant in designing of educational software (e-Learning). Principles and concepts of learning should be considered in addition to UID principles in UID for e-learning. In this regard, to specify the logical relationship between education, learning, UID and multimedia at first we readdress the issues raised in previous studies. It is followed by examining the principle concepts of e-learning and UID. Then, we will see how UID contributes to e-learning through the educational software built by authors. Also we show the way of using UI to improve learning and motivating the learners and to improve the time efficiency of using e-learning software.

Download

User Interface Design for E-Learning Software [for Music Education]

by Katebi Seraj, Mohammad Reza Azadehfar محمدرضا آزاده فر, and Behnam Faghih

The International Journal of Soft Computing and Software Engineering [JSCSE], Vol. 3, No. 3, Special Issue, 2013

User interface (UI) is point of interaction between user and computer software. The success and f... more User interface (UI) is point of interaction between user and computer software. The success and failure of a software application depends on User Interface Design (UID). Possibility of using a software, easily using and learning are issues influenced by UID. The UI is significant in designing of educational software (e-Learning). Principles and concepts of learning should be considered in addition to UID principles in UID for e-learning. In this regard, to specify the logical relationship between education, learning, UID and multimedia at first we readdress the issues raised in previous studies. It is followed by examining the principle concepts of e-learning and UID. Then, we will see how UID contributes to e-learning through the educational software built by authors. Also we show the way of using UI to improve learning and motivating the learners and to improve the time efficiency of using e-learning software.

Download

Real-time monophonic singing pitch detection

Pitch detection refers to algorithms for estimating the fundamental frequencies in an audio file ... more Pitch detection refers to algorithms for estimating the fundamental frequencies in an audio file and is usually one of the fundamental steps in processing sounds. However, although many solutions exist for speech, a perfect real-time pitch detector algorithm for singing is not yet available. Therefore, the two main objectives of this paper are: firstly, comparing several real-time pitch detection algorithms with different parameters to find the best ones for detecting the pitch from live monophonic singing. Secondly, finding a method to distinguish the set of correctly detected pitches. The parameters considered for comparison of the algorithms are the window size, hop size, gender, pitch interval, speed of performance, and post-processing applied. In addition, several evaluations of the pitch contours estimated by each of the algorithms have been conducted to assess both the accuracy and efficiency of each of the algorithms across the set of parameters. Finally, the best overall approach is identified after considering all the results, including the incorrect pitch assessment techniques.

Download

Uploads

Papers by Behnam Faghih

Drafts by Behnam Faghih

Log In