A New Method for Detecting Onset and Offset for Singing in Real-Time and Offline Environments
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 accura...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/15/7391 |
| _version_ | 1797442966360424448 |
|---|---|
| author | Behnam Faghih Sutirtha Chakraborty Azeema Yaseen Joseph Timoney |
| author_facet | Behnam Faghih Sutirtha Chakraborty Azeema Yaseen Joseph Timoney |
| author_sort | Behnam Faghih |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T12:50:14Z |
| format | Article |
| id | doaj.art-ad864a0996d64921acf725966fc76cd9 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T12:50:14Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-ad864a0996d64921acf725966fc76cd92023-11-30T22:08:18ZengMDPI AGApplied Sciences2076-34172022-07-011215739110.3390/app12157391A New Method for Detecting Onset and Offset for Singing in Real-Time and Offline EnvironmentsBehnam Faghih0Sutirtha Chakraborty1Azeema Yaseen2Joseph Timoney3Department of Computer Science, Maynooth University, W23 F2H6 Maynooth, Co. Kildare, IrelandDepartment of Computer Science, Maynooth University, W23 F2H6 Maynooth, Co. Kildare, IrelandDepartment of Computer Science, Maynooth University, W23 F2H6 Maynooth, Co. Kildare, IrelandDepartment of Computer Science, Maynooth University, W23 F2H6 Maynooth, Co. Kildare, IrelandThis 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.https://www.mdpi.com/2076-3417/12/15/7391real-time onset detectionsinging signal processingnote extractionsinging information retrieval |
| spellingShingle | Behnam Faghih Sutirtha Chakraborty Azeema Yaseen Joseph Timoney A New Method for Detecting Onset and Offset for Singing in Real-Time and Offline Environments Applied Sciences real-time onset detection singing signal processing note extraction singing information retrieval |
| title | A New Method for Detecting Onset and Offset for Singing in Real-Time and Offline Environments |
| title_full | A New Method for Detecting Onset and Offset for Singing in Real-Time and Offline Environments |
| title_fullStr | A New Method for Detecting Onset and Offset for Singing in Real-Time and Offline Environments |
| title_full_unstemmed | A New Method for Detecting Onset and Offset for Singing in Real-Time and Offline Environments |
| title_short | A New Method for Detecting Onset and Offset for Singing in Real-Time and Offline Environments |
| title_sort | new method for detecting onset and offset for singing in real time and offline environments |
| topic | real-time onset detection singing signal processing note extraction singing information retrieval |
| url | https://www.mdpi.com/2076-3417/12/15/7391 |
| work_keys_str_mv | AT behnamfaghih anewmethodfordetectingonsetandoffsetforsinginginrealtimeandofflineenvironments AT sutirthachakraborty anewmethodfordetectingonsetandoffsetforsinginginrealtimeandofflineenvironments AT azeemayaseen anewmethodfordetectingonsetandoffsetforsinginginrealtimeandofflineenvironments AT josephtimoney anewmethodfordetectingonsetandoffsetforsinginginrealtimeandofflineenvironments AT behnamfaghih newmethodfordetectingonsetandoffsetforsinginginrealtimeandofflineenvironments AT sutirthachakraborty newmethodfordetectingonsetandoffsetforsinginginrealtimeandofflineenvironments AT azeemayaseen newmethodfordetectingonsetandoffsetforsinginginrealtimeandofflineenvironments AT josephtimoney newmethodfordetectingonsetandoffsetforsinginginrealtimeandofflineenvironments |