Skip to main content
Springer Nature Link
Log in

Speech Music Overlap Detection Using Spectral Peak Evolutions

  • Conference paper
  • First Online:
Speech and Computer (SPECOM 2022)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 13721))

Included in the following conference series:

  • 1079 Accesses

Abstract

Speech-music overlap detection in audio signals is an essential preprocessing step for many high-level audio processing applications. Speech and music spectrograms exhibit characteristic harmonic striations that can be used as a feature for detecting their overlap. Hence, this work proposes two features generated using a spectral peak tracking algorithm to capture prominent harmonic patterns in spectrograms. One feature consists of the spectral peak amplitude evolutions in an audio interval. The second feature is designed as a Mel-scaled spectrogram obtained by suppressing non-peak spectral components. In addition, a one-dimensional convolutional neural network architecture is proposed to learn the temporal evolution of spectral peaks. Mel-spectrogram is used as a baseline feature to compare performances. A popular public dataset MUSAN with 102 h of data has been used to perform experiments. A late fusion of the proposed features with baseline is observed to provide better performance.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Anemüller, J., Schmidt, D., Bach, J.H.: Detection of speech embedded in real acoustic background based on amplitude modulation spectrogram features. In: Proceedings of the 9th Annual Conference of the International Speech Communication Association (2008)

    Google Scholar 

  2. Bach, J.H., Anemüller, J., Kollmeier, B.: Robust speech detection in real acoustic backgrounds with perceptually motivated features. Speech Commun. 53(5), 690–706 (2011)

    Article  Google Scholar 

  3. Bhattacharjee, M., Prasanna, S.R.M., Guha, P.: Speech/music classification using features from spectral peaks. IEEE/ACM Trans. Audio Speech Lang. Process. 28, 1549–1559 (2020)

    Google Scholar 

  4. Butko, T., Nadeu, C.: Audio segmentation of broadcast news in the Albayzin-2010 evaluation: overview, results, and discussion. EURASIP J. Audio Speech Music Process. 2011(1), 1–10 (2011)

    Google Scholar 

  5. Castán, D., Ortega, A., Miguel, A., Lleida, E.: Audio segmentation-by-classification approach based on factor analysis in broadcast news domain. EURASIP J. Audio Speech Music Process. 2014(1), 34 (2014)

    Google Scholar 

  6. Gimeno, P., Mingote, V., Ortega, A., Miguel, A., Lleida, E.: Partial AUC Optimisation using Recurrent Neural Networks for Music Detection with Limited Training Data. Proceedings. Interspeech, pp. 3067–3071 (2020)

    Google Scholar 

  7. Hershey, S., et al.: CNN architectures for large-scale audio classification. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 131–135 (2017)

    Google Scholar 

  8. Izumitani, T., Mukai, R., Kashino, K.: A background music detection method based on robust feature extraction. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 13–16 (2008)

    Google Scholar 

  9. Jia, B., Lv, J., Peng, X., Chen, Y., Yang, S.: Hierarchical regulated iterative network for joint task of music detection and music relative loudness estimation. IEEE/ACM Trans. Audio Speech Lang. Process. (2020)

    Google Scholar 

  10. Lee, K., Ellis, D.P.: Detecting music in ambient audio by long-window autocorrelation. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 9–12 (2008)

    Google Scholar 

  11. Lopez-Otero, P., Docio-Fernandez, L., Garcia-Mateo, C.: Ensemble audio segmentation for radio and television programmes. Multimedia Tools Appl. 76(5), 7421–7444 (2017)

    Article  Google Scholar 

  12. Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(Nov), 2579–2605 (2008)

    Google Scholar 

  13. Meng, H., Yan, T., Yuan, F., Wei, H.: Speech emotion recognition from 3D log-mel spectrograms with deep learning network. IEEE Access 7, 125868–125881 (2019)

    Article  Google Scholar 

  14. Mohammed, D.Y., Li, F.F.: Overlapped soundtracks segmentation using singular spectrum analysis and random forests. In: Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining, pp. 49–54 (2017)

    Google Scholar 

  15. Raj, B., Parikh, V.N., Stern, R.M.: The effects of background music on speech recognition accuracy. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 2, pp. 851–854 (1997)

    Google Scholar 

  16. Seyerlehner, K., Pohle, T., Schedl, M., Widmer, G.: Automatic music detection in television productions. In: Proceedings of the 10th International Conference on Digital Audio Effects (DAFx 2007). Citeseer (2007)

    Google Scholar 

  17. Sigurdsson, S., Petersen, K.B., Lehn-Schiøler, T.: Mel Frequency Cepstral Coefficients: An Evaluation of Robustness of MP3 Encoded Music. In: ISMIR, pp. 286–289 (2006)

    Google Scholar 

  18. Sinha, H., Awasthi, V., Ajmera, P.K.: Audio classification using braided convolutional neural networks (2020)

    Google Scholar 

  19. Snyder, D., Chen, G., Povey, D.: Musan: a music, speech, and noise corpus. arXiv preprint arXiv:1510.08484 (2015)

  20. Taniguchi, T., Tohyama, M., Shirai, K.: Detection of speech and music based on spectral tracking. Speech Commun. 50(7), 547–563 (2008)

    Article  Google Scholar 

  21. Umesh, S., Cohen, L., Nelson, D.: Fitting the Mel scale. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 1, pp. 217–220 (1999)

    Google Scholar 

  22. Vanroose, P.: Blind source separation of speech and background music for improved speech recognition. In: Proceedings of the 24th Symposium on Information Theory, pp. 103–108 (2003)

    Google Scholar 

  23. Vavrek, J., Fecil’ak, P., Juhár, J., Čižmár, A.: Classification of broadcast news audio data employing binary decision architecture. Comput. Inform. 36(4), 857–886 (2017)

    Article  MathSciNet  MATH  Google Scholar 

  24. Vavrek, J., Vozáriková, E., Pleva, M., Juhár, J.: Broadcast news audio classification using SVM binary trees. In: Proceedings of the 35th International Conference on Telecommunications and Signal Processing, pp. 469–473 (2012)

    Google Scholar 

  25. Weninger, F., Feliu, J., Schuller, B.: Supervised and semi-supervised suppression of background music in monaural speech recordings. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 61–64 (2012)

    Google Scholar 

  26. Zhang, T., Kuo, C.C.J.: Audio content analysis for online audiovisual data segmentation and classification. IEEE Trans. Speech Audio Process. 9(4), 441–457 (2001)

    Google Scholar 

Download references

Acknowledgments

Supported by Visvesvaraya PhD Scheme, MeitY, Govt. of India - MEITY-PHD-1230.

Author information

Authors and Affiliations

  1. Indian Institute of Technology Guwahati, Guwahati, 781039, Assam, India

    Mrinmoy Bhattacharjee & Prithwijit Guha

  2. Indian Institute of Technology Dharwad, Dharwad, 580011, Karnataka, India

    S. R. Mahadeva Prasanna

Authors
  1. Mrinmoy Bhattacharjee
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. S. R. Mahadeva Prasanna
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Prithwijit Guha
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mrinmoy Bhattacharjee .

Editor information

Editors and Affiliations

  1. Indian Institute of Technology Dharwad, Dharwad, India

    S. R. Mahadeva Prasanna

  2. St. Petersburg Federal Research Center of the Russian Academy of Sciences, St. Petersburg, Russia

    Alexey Karpov

  3. Koneru Lakshmaiah Education Foundation, Vaddeswaram, India

    K. Samudravijaya

  4. KIIT Group of Colleges, Gurugram, India

    Shyam S. Agrawal

Rights and permissions

Reprints and permissions

Copyright information

© 2022 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Bhattacharjee, M., Prasanna, S.R.M., Guha, P. (2022). Speech Music Overlap Detection Using Spectral Peak Evolutions. In: Prasanna, S.R.M., Karpov, A., Samudravijaya, K., Agrawal, S.S. (eds) Speech and Computer. SPECOM 2022. Lecture Notes in Computer Science(), vol 13721. Springer, Cham. https://doi.org/10.1007/978-3-031-20980-2_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20980-2_8

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20979-6

  • Online ISBN: 978-3-031-20980-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics