Výsledky vyhledávání - "Ryo Nishikimi"

Akademický článek

Global Structure-Aware Drum Transcription Based on Self-Attention Mechanisms

Autor: Ryoto Ishizuka, Ryo Nishikimi, Kazuyoshi Yoshii

Publikováno v: Signals, Vol 2, Iss 3, Pp 508-526 (2021)

This paper describes an automatic drum transcription (ADT) method that directly estimates a tatum-level drum score from a music signal in contrast to most conventional ADT methods that estimate the frame-level onset probabilities of drums. To estimat

Externí odkaz: https://doaj.org/article/c24f2c572b2349b39abcb34a5b93c99a

Zobrazit plný text záznamu

Bayesian Singing Transcription Based on a Hierarchical Generative Model of Keys, Musical Notes, and F0 Trajectories

Autor: Kazuyoshi Yoshii, Eita Nakamura, Masataka Goto, Katsutoshi Itoyama, Ryo Nishikimi

Publikováno v: IEEE/ACM Transactions on Audio, Speech, and Language Processing. 28:1678-1691

This article describes automatic singing transcription (AST) that estimates a human-readable musical score of a sung melody represented with quantized pitches and durations from a given music audio signal. To achieve the goal, we propose a statistica

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::bdab26cf42ab7a2590c229b72453b36c
https://doi.org/10.1109/taslp.2020.2996095

Zobrazit plný text záznamu

Global Structure-Aware Drum Transcription Based on Self-Attention Mechanisms

Autor: Kazuyoshi Yoshii, Ryo Nishikimi, Ryoto Ishizuka

Publikováno v: Signals
Volume 2
Issue 3
Pages 31-526
Signals, Vol 2, Iss 31, Pp 508-526 (2021)

This paper describes an automatic drum transcription (ADT) method that directly estimates a tatum-level drum score from a music signal, in contrast to most conventional ADT methods that estimate the frame-level onset probabilities of drums. To estima

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8c59b59b3d6638936117e26d7177c695

Zobrazit plný text záznamu

Pitch-Timbre Disentanglement Of Musical Instrument Sounds Based On Vae-Based Metric Learning

Autor: Shigeo Morishima, Keitaro Tanaka, Kazuyoshi Yoshii, Yoshiaki Bando, Ryo Nishikimi

Publikováno v: ICASSP

This paper describes a representation learning method for disentangling an arbitrary musical instrument sound into latent pitch and timbre representations. Although such pitch-timbre disentanglement has been achieved with a variational autoencoder (V

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::4cd8b92b4dd2f42afa0d8e9e7a5b100b
https://doi.org/10.1109/icassp39728.2021.9414059

Zobrazit plný text záznamu

Statistical Correction of Transcribed Melody Notes Based on Probabilistic Integration of a Music Language Model and a Transcription Error Model

Autor: Go Shibata, Eita Nakamura, Yuki Hiramatsu, Kazuyoshi Yoshii, Ryo Nishikimi

Publikováno v: ICASSP

This paper describes a statistical post-processing method for automatic singing transcription that corrects pitch and rhythm errors included in a transcribed note sequence. Although the performance of frame-level pitch estimation has been improved dr

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::11f9c4999d1b4d4a61fcc2e8fda13341
https://doi.org/10.1109/icassp39728.2021.9414249

Zobrazit plný text záznamu

Audio-to-score singing transcription based on a CRNN-HSMM hybrid model

Autor: Ryo Nishikimi, Eita Nakamura, Kazuyoshi Yoshii, Masataka Goto

Publikováno v: APSIPA Transactions on Signal and Information Processing. 10

This paper describes an automatic singing transcription (AST) method that estimates a human-readable musical score of a sung melody from an input music signal. Because of the considerable pitch and temporal variation of a singing voice, a naive casca

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::6b1681618f10f1865c4b5d8d9d49ed0d
https://doi.org/10.1017/atsip.2021.4

Zobrazit plný text záznamu

Music structure analysis based on an LSTM-HSMM hybrid model

Autor: Go Shibata, Ryo Nishikimi, Kazuyoshi Yoshii

This paper describes a statistical music structure analysis method that splits an audio signal of popular music into musically meaningful sections at the beat level and classifies them into predefined categories such as intro, verse, and chorus, wher

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0d460ab520f92e629b7a0949248dede9

Zobrazit plný text záznamu

Joint Singing Pitch Estimation and Voice Separation Based on a Neural Harmonic Structure Renderer

Autor: Yiming Wu, Kin Wah Edward Lin, Tomoyasu Nakano, Kazuyoshi Yoshii, Masataka Goto, Ryo Nishikimi

Publikováno v: WASPAA

This paper describes a multi-task learning approach to joint extraction (fundamental frequency (F0) estimation) and separation of singing voices from music signals. While deep neural networks have been used successfully for each task, both tasks have

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::c9359d492a7bc0ada4697481122fd9f6
https://doi.org/10.1109/waspaa.2019.8937135

Zobrazit plný text záznamu

End-To-End Melody Note Transcription Based on a Beat-Synchronous Attention Mechanism

Autor: Kazuyoshi Yoshii, Masataka Goto, Eita Nakamura, Ryo Nishikimi

Publikováno v: WASPAA

This paper describes an end-to-end audio-to-symbolic singing transcription method for mixtures of vocal and accompaniment parts. Given audio signals with non-aligned melody scores, we aim to train a recurrent neural network that takes as input a magn

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::0082a05c9a13fe747ef0f7010547bb33
https://doi.org/10.1109/waspaa.2019.8937207

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání