RWC Music Database: Music genre database and musical instrument sound database
By Masataka Goto, Hiroki Hashiguchi, T. Nishimura, R. Oka. International Society for Music Information Retrieval Conference, 2003
548 citations recorded by the source corpus.
View Paper: https://www.semanticscholar.org/paper/78dae646303057aff3ddc85ed7ed17a069fe2b9f
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Yoshua Bengio
- Sergey Levine
- Dacheng Tao
- Ruslan Salakhutdinov
- Bo Li
- Trevor Darrell
- Lior Wolf
- Kristen Grauman
Citations in the corpus
- Beyond NMF: Time-Domain Audio Source Separation without Phase Reconstruction (2013, methodology): “We used three mixture audio signals each of which was synthesized using piano sounds (011PFNOM), electric guitar sounds (131EGLPM), or clarinet sounds (311CLNOM) recorded in the RWC Music Database: Musical Instrument Sound [20].”
- On the optimality of ideal binary time-frequency masks (2008, methodology): “The music database is constructed from Bach’s works, each of which has two lines and each line of music is synthesized using instrument samples from the RWC database [19].”
- Invariances and Data Augmentation for Supervised Music Transcription (2017, methodology): “This alignment can be constructed using an optimal-alignment protocol, as in the SyncRWC [4], Lakh [6], and MusicNet [7] datasets.”
- A General Flexible Framework for the Handling of Prior Information in Audio Source Separation (2012, methodology): “, 8) are constrained toVj = W j G ex j 5 with G j being adaptive and W j being fixed and pre-trained (using our framework) from isolated bass and drum samples from the RWC music database [53].”
- Deep neural network based instrument extraction from music (2015, methodology): “In a second step, we convert all signals into the frequency domain using a STFT and randomly sample from the target and background instruments P complex-valued STFT vectors {s(1), .”
- Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders (2017, background): “While several smaller datasets currently exist (Goto et al., 2003; Romani Picas et al., 2015), deep networks train better on abundant, highquality data, motivating the development of a new dataset.”