Melody analysis for prediction of the emotions conveyed by Sinhala songs

Lakshitha, M.G. Viraj; Jayaratne, K. L.

doi:10.1109/iciafs.2016.7946524

Cited by 5 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For an example, non-song audio objects have high value for zero crossing rate than song objects. MPEG-7 descriptors, entropy and octaves are also used to analyse audio objects, for more details please refer [11] [12] [13] [20].…”

Section: Related Workmentioning

confidence: 99%

Radio Broadcast Monitoring to Ensure Copyright Ownership

Senevirathna

Jayaratne

2018

Int J on Adv. in ICT for Emerging Countries

View full text Add to dashboard Cite

In this research, we provide a way to protect copyright ownership of multimedia objects like songs. Protecting ownership is very important when we are working in a corporative environment. If someone tries to misuse others' property it is an illegal action. But capturing theses kind of actions especially on electronic objects are very difficult. There are several ways to share copyright ownership with others. We can purchase others' property and use them under conditions provided by the owner. In this research, we are focusing on protecting ownership of audio songs broadcasted by radio channels. There are so many radio channels in a country, as well as a huge number of songs are broadcasted per day. In order to broadcast particular song in a radio channel, they should purchase the right to do so. In order to make sure that this process is functioning correctly, we have to monitor radio channel and extract the broadcasted songs. Currently, this is happened manually. Manual process is no longer able to continue because the number of songs is increasing day by day. We provide an automated solution for this real-world problem. There are so many researches on this area done by various researches. They used different approaches to achieve the final goal. Most of them have used content base audio identification base approaches. In this context, an unknown audio file is identified by analysing the content of it. But, it is very hard to find researches that use this concept to monitor radio channel since there are additional complexities when we come to monitor radio channel. In this research, we extend the content-based audio identification approach to monitor radio channel automatically. First, we perform a pre-process on raw audio objects that broadcasted by a radio channel. After extracting interest areas, we generate set of hash values. Then, we perform powerful approximate matching against pre-stored hashes. Ultimately, we provide a detailed report which contains all the information of broadcasted audio songs.

show abstract

Section: Related Workmentioning

confidence: 99%

Radio Broadcast Monitoring to Ensure Copyright Ownership

Senevirathna

Jayaratne

2018

Int J on Adv. in ICT for Emerging Countries

View full text Add to dashboard Cite

show abstract

“…Authorized people in mass media and information corporations need to track the FM channels regularly to ensure whether the broadcasting contents adhere to the rules and regulations and has a diversity of available programs. Singers and composers need monitoring of songs to claim their rights [9,10,11,12,13]. Advertising agents are keen on the frequencies of the advertisement broadcasting that have a huge impact on their corporate income.…”

Section: Introductionmentioning

confidence: 99%

Classification of Voice Content in the Context of Public Radio Broadcasting

Karunarathna

Jayaratne

Gunawardana

2020

Int J on Adv. in ICT for Emerging Countries

View full text Add to dashboard Cite

With the rapid development of mass media technology, content classification of radio broadcasting has emerged as a major research area facilitating the automation of radio broadcasting monitoring process. This research focuses on the voice dominant content classification of radio broadcasting by employing a multi-class Support Vector Machine (SVM) in order to automate monitoring of radio broadcasting in Sri Lanka. This study investigates the performance of "One Vs. One" and "One Vs. All" methods known to be two conventional ways to build a multi-class SVM. These two multi-class SVM models are trained to classify five voice dominant classes as news, conversations, and advertisements without jingles, radio drama and religious programs.One of the substantial measures in creating such a classification is selection of the optimal feature sets. For that purpose, time domain features, frequency domain features, cepstral features, and chroma features are manually analyzed for each binary SVM classifier independently. Two multi-class SVM models are trained based on the selected features and the "One Vs. One" model was able to better classify the recordings with an 85% accuracy compared to 83% accuracy achieved by "One Vs. All" model. Further, the results revealed the importance of careful feature selection in order to achieve higher classification accuracies.

show abstract

Automated audio monitoring approach for radio broadcasting channels in Sri Lanka

Senevirathna

Jayaratne

2017

2017 Seventeenth International Conference on Advances in ICT for Emerging Regions (ICTer)

View full text Add to dashboard Cite

Melody analysis for prediction of the emotions conveyed by Sinhala songs

Cited by 5 publications

References 13 publications

Radio Broadcast Monitoring to Ensure Copyright Ownership

Radio Broadcast Monitoring to Ensure Copyright Ownership

Classification of Voice Content in the Context of Public Radio Broadcasting

Automated audio monitoring approach for radio broadcasting channels in Sri Lanka

Contact Info

Product

Resources

About