| 講演名 | 2024-02-29 A Study on Automatic Performance System for Emulating the Playing Style of a Specific Pianist using Feature Extraction with LSTM and Score Analys 李 森浩(日大), 松野 裕(日大), |
|---|---|
| PDFダウンロードページ |  PDFダウンロードページへ |
| 抄録(和) | Classical music continues to captivate audiences worldwide, and advancements in automatic piano playing technologies and the Internet allows people to enjoy professional piano performances at home. However, the labor-intensive process of recording tracks on sensor-equipped pianos and the limited repertoire available present challenges. Thus, in this paper, we propose a neural network?based method to generate automatic piano performances. The proposed method utilizes long short-term memory (LSTM) networks, designed for the specific pianist, and contributes to the field of music notation learning. We employ LSTM networks rather than a recurrent neural network to decipher and encapsulate the intricate temporal dependencies characteristic of piano performances. We conducted training loss evaluation and pianist perception assessment. Experimental outcomes demonstrated predictive accuracy with R-squared (R?) values between 0.4 and 0.6. Blind listening tests revealed the model's effectiveness in generating performances that are comparable to those of skilled pianists. |
| 抄録(英) | Classical music continues to captivate audiences worldwide, and advancements in automatic piano playing technologies and the Internet allows people to enjoy professional piano performances at home. However, the labor-intensive process of recording tracks on sensor-equipped pianos and the limited repertoire available present challenges. Thus, in this paper, we propose a neural network?based method to generate automatic piano performances. The proposed method utilizes long short-term memory (LSTM) networks, designed for the specific pianist, and contributes to the field of music notation learning. We employ LSTM networks rather than a recurrent neural network to decipher and encapsulate the intricate temporal dependencies characteristic of piano performances. We conducted training loss evaluation and pianist perception assessment. Experimental outcomes demonstrated predictive accuracy with R-squared (R?) values between 0.4 and 0.6. Blind listening tests revealed the model's effectiveness in generating performances that are comparable to those of skilled pianists. |
| キーワード(和) | |
| キーワード(英) | LSTMFeature ExtractionMusical Notation |
| 資料番号 | EA2023-76,SIP2023-123,SP2023-58 |
| 発行日 | 2024-02-22 (EA, SIP, SP) |
| 研究会情報 | |
| 研究会 | SIP / SP / EA / IPSJ-SLP |
|---|---|
| 開催期間 | 2024/2/29(から2日開催) |
| 開催地（和） | 沖縄産業支援センター |
| 開催地（英） | |
| テーマ（和） | 音声，応用／電気音響, 信号処理，一般 |
| テーマ（英） | |
| 委員長氏名（和） | 仲地 孝之(琉球大) / 戸田 智基(名大) / 小野 順貴(都立大) |
| 委員長氏名（英） | Takayuki Nakachi(Ryukyu Univ.) / Tomoki Toda(Nagoya Univ.) / Junki Ono(Tokyo Metropolitan Univ.) |
| 副委員長氏名（和） | 市毛 弘一(横浜国大) / 西川 清史(都立大) / / 西浦 敬信(立命館大) / 梶川 嘉延(関西大) |
| 副委員長氏名（英） | Koichi Ichige(Yokohama National Univ.) / Kiyoshi Nishikawa(okyo Metropolitan Univ.) / / Takanobu Nishiura(RitsumeikanUniv.) / Yoshinobu Kajikawa(Kansai Univ.) |
| 幹事氏名（和） | 今泉 祥子(千葉大) / 京地 清介(工学院大) / 安藤 厚志(NTT) / 橋本 佳(名工大) / 若山 圭吾(NTT) / 伊藤 信貴(東大) |
| 幹事氏名（英） | Shoko Imaizumi(Chiba Univ.) / Seisuke Kyochi(Kogakuin Univ.) / Atsushi Ando(NTT) / Kei Hashimoto(Nagoya Inst. of Tech.) / Keigo Wakayama(NTT) / Nobutaka Ito(Univ. of Tokyo) |
| 幹事補佐氏名（和） | 吉田 太一(電通大) / 塩田 さやか(都立大) / 相原 龍(三菱電機) / 齋藤 大輔(東大) / 中山 雅人(阪産大) / 矢田部 浩平(東京農工大) |
| 幹事補佐氏名（英） | Taichi Yoshida(UEC) / Sayaka Shiota(Tokyo Metropolitan Univ.) / Ryo Aihara(Mitsubishi Electric) / Daisuke Saito(Univ. of Tokyo) / Masato Nakayama(OSU) / Kouhei Yatabe(TUAT) |
| 講演論文情報詳細 | |
| 申込み研究会 | Technical Committee on Signal Processing / Technical Committee on Speech / Technical Committee on Engineering Acoustics / Special Interest Group on Spoken Language Processing |
|---|---|
| 本文の言語 | ENG |
| タイトル（和） | |
| サブタイトル（和） | |
| タイトル（英） | A Study on Automatic Performance System for Emulating the Playing Style of a Specific Pianist using Feature Extraction with LSTM and Score Analys |
| サブタイトル（和） | |
| キーワード(1)（和/英） | / LSTMFeature ExtractionMusical Notation |
| 第 1 著者 氏名（和/英） | 李 森浩 / Li Senhao |
| 第 1 著者 所属（和/英） | 日本大学(略称：日大) Nihon University(略称：Nihon Univ.) |
| 第 2 著者 氏名（和/英） | 松野 裕 / Matsuno Yutaka |
| 第 2 著者 所属（和/英） | 日本大学(略称：日大) Nihon University(略称：Nihon Univ.) |
| 発表年月日 | 2024-02-29 |
| 資料番号 | EA2023-76,SIP2023-123,SP2023-58 |
| 巻番号（vol） | vol.123 |
| 号番号（no） | EA-401,SIP-402,SP-403 |
| ページ範囲 | pp.91-96(EA), pp.91-96(SIP), pp.91-96(SP), |
| ページ数 | 6 |
| 発行日 | 2024-02-22 (EA, SIP, SP) |