Publications
Publications
Kanami Imamura, Tomohiko Nakamura, Norihiro Takamune, Kohei Yatabe, and Hiroshi Saruwatari, “Stride conversion algorithms for convolutional layers and its application to sampling-frequency-independent deep neural networks,” Signal Processing, vol. 242, pp. 110420, May, 2026.
[paper] [code]
Kanami Imamura, Tomohiko Nakamura, Kohei Yatabe, and Hiroshi Saruwatari, “Neural analog filter for sampling-frequency-independent convolutional layer,” APSIPA Transactions on Signal and Information Processing, vol. 13, no. 1, e28, Nov. 2024.
[paper] [code1] [code2] [slide] [poster]
Go Nishikawa, Wataru Nakata, Yuki Saito, Kanami Imamura, Hiroshi Saruwatari, and Tomohiko Nakamura, “Multi-sampling-frequency naturalness MOS prediction using self-supervised learning model with sampling-frequency-independent layer,” in Proceedings of IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2025. (First and second authors contributed equally.)
[arXiv] [code]
Kanami Imamura, Tomohiko Nakamura, Norihiro Takamune, Kohei Yatabe, and Hiroshi Saruwatari, “Local equivariance error-based metrics for evaluating sampling-frequency-independent property of neural network,” in Proceedings of European Signal Processing Conference (EUSIPCO), 2025, pp.276–280.
[paper] [arXiv] [poster]
Kentaro Seki, Shinnosuke Takamichi, Norihiro Takamune, Yuki Saito, Kanami Imamura, and Hiroshi Saruwatari, “Spatial Voice Conversion: Voice Conversion Preserving Spatial Information and Non-target Signals” in Proceedings of INTERSPEECH, 2024, pp. 177–181.
[paper] [arXiv]
Kanami Imamura, Tomohiko Nakamura, Norihiro Takamune, Kohei Yatabe, and Hiroshi Saruwatari, “Algorithms of sampling-frequency-independent layers for non- integer stride,” in Proceedings of The European Signal Processing Conference (EUSIPCO), 2023, pp. 326–330.
[paper] [arXiv] [poster]
Shogo Seki, Kanami Imamura, Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, and Noboru Harada, “W2N-AVSC: Audiovisual extension for whisper-to-normal speech conversion,” in Proceedings of The European Signal Processing Conference (EUSIPCO), 2023, pp. 296–300.
[paper]
Kanami Imamura, Tomohiko Nakamura, Kohei Yatabe, and Hiroshi Saruwatari, “Continuous function approximation of convolutional kernels for sampling frequency adaptation of pre-trained source separation networks,” in Proceedings of Joint Meeting of the Acoustical Society of America and the Acoustical Society of Japan, 2025 (Abstract reviewed).
[poster]
Kanami Imamura, Tomohiko Nakamura, Norihiro Takamune, and Hiroshi Saruwatari, “Handling method for non-integer hopsize in sampling-frequency-independent layers,” in University of Auckland and UTokyo Joint Workshop on Extreme Acoustic Sensing Based on Small-Data-Driven Machine Learning and Its Rescue Application, 2023 (Presentation only).
[slide]
西川 剛，中田 亘，齋藤 佑樹，今村 奏海，猿渡 洋，“サンプリング周波数非依存畳み込み層を導入した自己教師あり学習モデルによるマルチサンプリングレート自然性MOS予測，”日本音響学会 秋季研究発表会, 1-1-17, pp. 1171--1174, Sep. 2025．
今村 奏海，中村 友彦，高宗 典玄，矢田部 浩平，猿渡 洋，“Local equivariance Errorに基づくサンプリング周波数非依存性評価指標の提案と分析，”電子情報通信学会技術研究報告，vol. 124，pp. 193–198，Mar. 2025．
[slide]
今村 奏海，中村 友彦，高宗 典玄，矢田部 浩平，猿渡 洋，“Local equivariance errorに基づくサンプリング周波数非依存性評価指標の検討，”日本音響学会2024年秋期研究発表会, pp. 241–244, Sep. 2024．
[poster]
今村 奏海，中村 友彦，高宗 典玄，矢田部 浩平，猿渡 洋，“非整数ストライド処理アルゴリズムを用いたサンプリング周波数非依存畳み込み層による楽音分離の実験的評価，”情報処理学会研究報告，vol. 2024–MUS–140，May 2024．
[poster]
今村奏海，中村友彦，高宗典玄，矢田部浩平，猿渡洋，“サンプリング周波数非依存畳み込み層における非整数ストライド処理アルゴリズム，”日本音響学会2023年秋季研究発表 会，pp. 157–160，Sep. 2023．
[slide]
今村奏海，中村友彦，矢田部浩平，猿渡洋，“サンプリンング周波数非依存畳み込み層のための時間領域ニューラルアナログフィルタ，”日本音響学会2022年秋季研究発表会，pp. 187–190，Sep. 2022．
[slide]
今村奏海，増田尚建，須田仁志，齋藤大輔，峯松信明，“自然音声の人工感を連続的に制御する技術の検討と評価，”日本音響学会2022年春季研究発表会，pp. 827–830，Mar. 2022．
[slide]