説明:
(abstract)In this study, we investigated the processing capability required for PRC-only speech recognition by systematically comparing the presence and absence of cochleagram preprocessing and PRC. As the physical reservoir, we employed a nonlinear interfered spin-wave PRC exhibiting input-frequency-dependent responses. Two speech-recognition tasks, spoken digit recognition and speaker classification, were evaluated under all combinations of cochleagram preprocessing and PRC processing. When cochleagram preprocessing was employed, both tasks achieved high-recognition accuracy. In contrast, using only the spin-wave PRC yielded approximately 84.6 % accuracy for speaker classification, whereas spoken digit recognition remained 29.0 %. Furthermore, spoken digit recognition accuracy improved when the speaker was fixed, whereas speaker classification maintained relatively high accuracy even when the spoken digit was fixed. These results indicate that speaker classification and spoken digit recognition require different types of processing in the present spin-wave PRC and provide useful insight into the processing capability required for PRC-only speech recognition.
権利情報:
This article may be downloaded for personal use only. Any other use requires prior permission of the author and AIP Publishing. This article appeared in Sota Hikasa, Wataru Namiki, Daiki Nishioka, Ryo Iguchi, Jiaxuan Chen, Maki Nishimura, Kazuya Terabe, Takashi Tsuchiya; Investigating the cochleagram preprocessing and the role of interfered spin-wave-based reservoir computing in speech recognition. J. Appl. Phys. 28 September 2026; 140 (12): 123908 and may be found at https://doi.org/10.1063/5.0333726.
キーワード: reservoir computing, spin wave, speech recognition
刊行年月日: 2026-09-28
出版者: AIP Publishing
掲載誌:
研究助成金:
原稿種別: 著者最終稿 (Accepted manuscript)
MDR DOI: https://doi.org/10.48505/nims.8665
公開URL: https://doi.org/10.1063/5.0333726
関連資料:
その他の識別子:
連絡先:
更新時刻: 2026-10-19 09:16:28 +0900
MDRでの公開時刻: 2026-10-19 10:30:09 +0900
| ファイル名 | サイズ | |||
|---|---|---|---|---|
| ファイル名 |
JAP_Hikasa_revised-v2_nohighlight.docx
(サムネイル)
application/vnd.openxmlformats-officedocument.wordprocessingml.document |
サイズ | 23.3MB | 詳細 |