# Investigating the cochleagram preprocessing and the role of interfered spin-wave-based reservoir computing in speech recognition

https://mdr.nims.go.jp/datasets/cd55d153-98dc-4a83-bd5c-74754406aa22

## File

- [JAP_Hikasa_revised-v2_nohighlight.docx](https://mdr.nims.go.jp/filesets/df22a176-7bd7-4633-b652-b7c739839811/download) ([Detail](https://mdr.nims.go.jp/filesets/df22a176-7bd7-4633-b652-b7c739839811.md))

## Id

cd55d153-98dc-4a83-bd5c-74754406aa22

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2026-10-16T05:06:13.144198Z

## Updated at

2026-10-19T00:16:28.310254Z

## Published at

2026-10-19T01:30:09.517541Z

## Doi

https://doi.org/10.48505/nims.8665

## First published url

https://doi.org/10.1063/5.0333726

## Date published

2026-09-28

## Recorded date published

2026-9-28

## Resource type

journal_article

## Manuscript type

accepted_manuscript

## Collection



## Title

- title: Investigating the cochleagram preprocessing and the role of interfered spin-wave-based
    reservoir computing in speech recognition
  title_type: original
  lang: en

## Description

- description: 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.
  description_type: abstract
  lang: und

## Creator

- name: Sota Hikasa
  role: author
  orcid: https://orcid.org/0009-0005-0888-1783
  organization: National Institute for Materials Science
- name: Wataru Namiki
  role: author
  orcid: https://orcid.org/0000-0003-4053-7366
  organization: National Institute for Materials Science
- name: Daiki Nishioka
  role: author
  orcid: https://orcid.org/0000-0002-3369-7700
  organization: National Institute for Materials Science
- name: Ryo Iguchi
  role: author
  orcid: https://orcid.org/0000-0002-8112-4608
  organization: National Institute for Materials Science
- name: Jiaxuan Chen
  role: author
  organization: National Institute for Materials Science
- name: Maki Nishimura
  role: author
  orcid: https://orcid.org/0009-0005-5265-7180
  organization: National Institute for Materials Science
- name: Kazuya Terabe
  role: author
  orcid: https://orcid.org/0000-0003-3988-3456
  organization: National Institute for Materials Science
- name: Takashi Tsuchiya
  role: author
  orcid: https://orcid.org/0000-0002-6950-6160
  organization: National Institute for Materials Science

## Contact agent



## Publisher

organization: AIP Publishing

## Managing organization



## Keyword

- subject: reservoir computing
  schema: not_defined
- subject: spin wave
  schema: not_defined
- subject: speech recognition
  schema: not_defined

## Rights

- description: '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.'
  identifier: http://rightsstatements.org/vocab/InC/1.0/

## Other identifier(s)



## Data origin

- data_origin_type: other

## Embargo



## Journal

- title: Journal of Applied Physics
  issn: '00218979'
  volume: '140'
  issue: '12'
  article_number: '123908'

## Conference



## Related item



## Funding

- identifier: JPJ004596
  funder_name: Innovative Science and Technology Initiative for Security
- identifier: JP25K17658
  funder_name: Japan Society for the Promotion of Science
- identifier: JPMXP1225NM5244
  funder_name: Ministry of Education, Culture, Sports, Science and Technology

## Instrument



## Instrument operator



## Instrument managing organization



## Measurement method



## Specimen



## Chemical composition



## Structure for specimen



## Structural feature for specimen



## Specific property for specimen



## Process for specimen treatment



## Computational method



## Energy level/transition state



## Software



## Custom property



## Fileset

- id: df22a176-7bd7-4633-b652-b7c739839811
  filename: JAP_Hikasa_revised-v2_nohighlight.docx
  content_type: application/vnd.openxmlformats-officedocument.wordprocessingml.document
  size: 24407457
  md5: 3e4c5f5345904cf4c4ccdb3d3e9b36eb

## Thumbnail

fileset_id: df22a176-7bd7-4633-b652-b7c739839811
filename: JAP_Hikasa_revised-v2_nohighlight.docx