End-to-end sound source separation conditioned on instrument labels

Inicio | ¿Qué es? | Contacto

English | Català

Consultar RECERCAT

Por comunidades y
colecciones Por fecha Por autores Por títulos Por temas (CDU)

Consultar departamento

Por fecha Por autores Por títulos Por temas (CDU)

Estadisticas

Del documento Todo RECERCAT

Mi RECERCAT

Entrar Alertas por correo-e

Directorio de otros repositorios

RECERCAT Principal > Universitat Pompeu Fabra > Articles, congressos, llibres > Visualizar documento

Para acceder a los documentos con el texto completo, por favor, siga el siguiente enlace: http://hdl.handle.net/10230/37258

Título:	End-to-end sound source separation conditioned on instrument labels
Autor/a:	Slizovskaia, Olga; Kim, Leo; Haro Ortega, Gloria; Gómez Gutiérrez, Emilia, 1975-
Abstract:	Comunicació presentada a: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing celebrat de 12 al 17 de maig de 2019 a Brighton, Regne Unit.
Abstract:	Can we perform an end-to-end music source separation with a variable number of sources using a deep learning model? This paper presents an extension of the Wave-UNet [1] model which allows end-to-end monaural source separation with a non-fixed number of sources. Furthermore, we propose multiplicative conditioning with instrument labels at the bottleneck of the Wave-U-Net and show its effect on the separation results. This approach can be further extended to other types of conditioning such as audio-visual source separation and score-informed source separation.
Abstract:	This work has received funding from the Maria de Maeztu Programme (MDM-2015-0502), ERC Innovation Programme (grant 770376, TROMPA), and MINECO/FEDER UE project (TIN2015-70410-C2-1-R).
Materia(s):	-Sound source separation -End-to-end deep learning -Wave-U-Net
Derechos:	info:eu-repo/semantics/embargoedAccess © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. http://dx.doi.org/10.1109/ICASSP.2019.8683800
Tipo de documento:	Objeto de conferencia Artículo - Versión aceptada
Editor:	Institute of Electrical and Electronics Engineers (IEEE)
Compartir:

Mostrar el registro completo del ítem

Documentos relacionados

Otros documentos del mismo autor/a

Automatic musical instrument recognition in audiovisual recordings by combining image and audio classification strategies

Slizovskaia, Olga; Gómez Gutiérrez, Emilia, 1975-; Haro Ortega, Gloria

Correspondence between audio and visual deep models for musical instrument detection in video recordings

Slizovskaia, Olga; Gómez Gutiérrez, Emilia, 1975-; Haro Ortega, Gloria

Musical instrument recognition in user-generated videos using a multimodal convolutional neural network architecture

Slizovskaia, Olga; Gómez Gutiérrez, Emilia, 1975-; Haro Ortega, Gloria

Acoustic scene classification by ensembling gradient boosting machine and convolutional neural networks

Fonseca, Eduardo; Gong, Rong; Bogdanov, Dmitry; Slizovskaia, Olga; Gómez Gutiérrez, Emilia, 1975-; Serra, Xavier

Timbre analysis of music audio signals with convolutional neural networks

Pons Puig, Jordi; Slizovskaia, Olga; Gómez Gutiérrez, Emilia, 1975-; Serra, Xavier

Accesibilidad | Aviso legal | Política de Cookies | Documentos de uso interno

Coordinación

Patrocinio