View in EDS HTML Full Text PDF Full Text

Multi-resolution spectrogram based multi-branch hybrid attention network for music emotion recognition.

Saved in:
Bibliographic Details
Title: Multi-resolution spectrogram based multi-branch hybrid attention network for music emotion recognition.
Authors: Su, Yuping1,2 (AUTHOR) ypsu@snnu.edu.cn, Chai, Ruiting1,2 (AUTHOR) chairt@snnu.edu.cn, Yang, Honghong2,3 (AUTHOR) yanghonghong@snnu.edu.cn, Wu, Xiaojun1,2,3 (AUTHOR) xjwu@snnu.edu.cn, Sun, Weitong4 (AUTHOR) swt@snnu.edu.cn
Source: EURASIP Journal on Audio Speech & Music Processing. 3/28/2026, Vol. 2026 Issue 1, p1-16. 16p.
Subjects: Spectrograms, Emotion recognition, Feature extraction
Abstract: Music emotion recognition (MER) is a critical task in the field of music information retrieval. However, most MER research relies solely on single-scale music spectrograms and fails to consider the complementary effects of spectrograms at different scales. Meanwhile, fully extracting emotion-related information from spectrograms remains a major challenge in MER. In this paper, we propose a hybrid attention model based on multi-resolution spectrograms, named MSMHA. The MSMHA model takes multi-scale Mel-spectrograms as inputs, and each input is fed into a well-designed hybrid attention network. The designed attention network successively includes a low-level feature extraction module, a local feature extraction module based on window attention, a channel attention-based long skip connection module, a high-level feature extraction module, and a branch classifier. After being processed by the hybrid attention network, each branch can fully extract emotion-related semantic features from a spectrogram of the specific resolution and output an emotion-classification probability. Finally, a decision-level weighted fusion strategy is applied to the multi-branch outputs to generate the final classification results. The experimental results on the PMEmo dataset demonstrate that our model is both promising and effective, achieving classification accuracies of 90.9%, 86.36%, and 79.87% on the binary-arousal, binary-valence, and four-quadrant dimensions, respectively. Ablation studies further confirm the effectiveness of both the multi-resolution spectrogram inputs and each module of the hybrid attention network. [ABSTRACT FROM AUTHOR]
Copyright of EURASIP Journal on Audio Speech & Music Processing is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 193681635
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Multi-resolution spectrogram based multi-branch hybrid attention network for music emotion recognition.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Su%2C+Yuping%22">Su, Yuping</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> ypsu@snnu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Chai%2C+Ruiting%22">Chai, Ruiting</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> chairt@snnu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Yang%2C+Honghong%22">Yang, Honghong</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<i> yanghonghong@snnu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Wu%2C+Xiaojun%22">Wu, Xiaojun</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<i> xjwu@snnu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Sun%2C+Weitong%22">Sun, Weitong</searchLink><relatesTo>4</relatesTo> (AUTHOR)<i> swt@snnu.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22EURASIP+Journal+on+Audio+Speech+%26+Music+Processing%22">EURASIP Journal on Audio Speech & Music Processing</searchLink>. 3/28/2026, Vol. 2026 Issue 1, p1-16. 16p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Spectrograms%22">Spectrograms</searchLink><br /><searchLink fieldCode="DE" term="%22Emotion+recognition%22">Emotion recognition</searchLink><br /><searchLink fieldCode="DE" term="%22Feature+extraction%22">Feature extraction</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Music emotion recognition (MER) is a critical task in the field of music information retrieval. However, most MER research relies solely on single-scale music spectrograms and fails to consider the complementary effects of spectrograms at different scales. Meanwhile, fully extracting emotion-related information from spectrograms remains a major challenge in MER. In this paper, we propose a hybrid attention model based on multi-resolution spectrograms, named MSMHA. The MSMHA model takes multi-scale Mel-spectrograms as inputs, and each input is fed into a well-designed hybrid attention network. The designed attention network successively includes a low-level feature extraction module, a local feature extraction module based on window attention, a channel attention-based long skip connection module, a high-level feature extraction module, and a branch classifier. After being processed by the hybrid attention network, each branch can fully extract emotion-related semantic features from a spectrogram of the specific resolution and output an emotion-classification probability. Finally, a decision-level weighted fusion strategy is applied to the multi-branch outputs to generate the final classification results. The experimental results on the PMEmo dataset demonstrate that our model is both promising and effective, achieving classification accuracies of 90.9%, 86.36%, and 79.87% on the binary-arousal, binary-valence, and four-quadrant dimensions, respectively. Ablation studies further confirm the effectiveness of both the multi-resolution spectrogram inputs and each module of the hybrid attention network. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of EURASIP Journal on Audio Speech & Music Processing is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=193681635
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1186/s13636-026-00460-7
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 16
        StartPage: 1
    Subjects:
      – SubjectFull: Spectrograms
        Type: general
      – SubjectFull: Emotion recognition
        Type: general
      – SubjectFull: Feature extraction
        Type: general
    Titles:
      – TitleFull: Multi-resolution spectrogram based multi-branch hybrid attention network for music emotion recognition.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Su, Yuping
      – PersonEntity:
          Name:
            NameFull: Chai, Ruiting
      – PersonEntity:
          Name:
            NameFull: Yang, Honghong
      – PersonEntity:
          Name:
            NameFull: Wu, Xiaojun
      – PersonEntity:
          Name:
            NameFull: Sun, Weitong
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 28
              M: 03
              Text: 3/28/2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 16874714
          Numbering:
            – Type: volume
              Value: 2026
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: EURASIP Journal on Audio Speech & Music Processing
              Type: main
ResultId 1