Logo Kérwá
 

Semi-supervised audio source separation based on the iterative estimation and extraction of note events

dc.creatorDelgado Castro, Alejandro
dc.creatorSzymanski, John Edward
dc.date.accessioned2024-10-23T16:39:19Z
dc.date.available2024-10-23T16:39:19Z
dc.date.issued2019-07-28
dc.description.abstractIn this paper, we present an iterative semi-automatic audio source separation process for single-channel polyphonic recordings, where the underlying sources are isolated by clustering a set of note events, which are considered to be single notes or groups of consecutive notes coming from the same source. In every iteration, an automatic process detects the pitch trajectory of the predominant note event in the mixture, and separates its spectral content from the mixed spectrogram. The predominant note event is then transformed back to the time-domain and subtracted from the input mixture. The process repeats using the residual as the new input mixture, until a predefined number of iterations is reached. When the iterative stage is complete, note events are clustered by the end-user to form individual sources. Evaluation is conducted on mixtures of real instruments and compared with a similar approach, revealing an improvement in separation quality.
dc.description.procedenceUCR::Sedes Regionales::Sede de Guanacaste
dc.description.procedenceUCR::Vicerrectoría de Docencia::Ingeniería::Facultad de Ingeniería::Escuela de Ingeniería Eléctrica
dc.description.sponsorshipMinisterio de Ciencia, Innovación, Tecnología, y Telecomunicaciones/[]/MICITT/Costa Rica
dc.description.sponsorshipUniversidad de Costa Rica/[]/UCR/Costa Rica
dc.identifier.citationhttps://www.scitepress.org/Link.aspx?doi=10.5220/0007828002730279
dc.identifier.doi10.5220/0000125500002330
dc.identifier.isbn978-989-758-378-0
dc.identifier.issn2184-3236
dc.identifier.urihttps://hdl.handle.net/10669/99932
dc.language.isoeng
dc.sourceProceedings of the 16th International Joint Conference on e-Business and Telecommunications (ICETE 2019), 1, 273-279
dc.subjectAudio Source Separation
dc.subjectNote Event Detection
dc.subjectFundamental Frequency Estimation
dc.subjectNote Event Tracking
dc.subjectSeparation of Overlapping Harmonics
dc.subjectTime-domain Subtraction
dc.subjectSemi-supervised Estimation
dc.titleSemi-supervised audio source separation based on the iterative estimation and extraction of note events
dc.typecomunicación de congreso

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
6-Semi_Supervised_Audio_Separation_SIGMAP2019.pdf
Size:
1.18 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
3.5 KB
Format:
Item-specific license agreed upon to submission
Description: