Advertisement

A Practical Singing Voice Detection System Based on GRU-RNN

  • Zhigao Chen
  • Xulong Zhang
  • Jin Deng
  • Juanjuan Li
  • Yiliang Jiang
  • Wei LiEmail author
Conference paper
  • 204 Downloads
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 568)

Abstract

In this paper, we present a practical three-step approach for singing voice detection based on a gated recurrent unit (GRU) recurrent neural network (RNN) and the proposed method achieves comparable results to state-of-the-art method. We combine four classic features—namely Mel-frequency Cepstral Coefficients (MFCC), Mel-filter Bank, Linear Predictive Cepstral Coefficients (LPCC), and Chroma. Then, the mixed signal is first preprocessed by singing voice separation (SVS) with the Deep U-Net Convolutional Networks. Long short-term memory (LSTM) and GRU are both proposed to solve the gradient vanish problem in RNN. In our experiments, we set the block duration as 120 ms and 720 ms respectively, and we get comparable or better results than results from state-of-the-art methods, while results on Jamendo are not as good as those from RWC-Pop.

Keywords

Singing voice detection (SVD) Gated recurrent unit (GRU) Recurrent neural network (RNN) Music information retrieval (MIR) 

Notes

Acknowledgements

This research was supported by NSFC 61671156. We thank our colleagues from Fudan University, who provided insight and expertise that greatly assisted the research, although they may not agree with all the interpretations of this paper.

References

  1. 1.
    Leglaive S, Hennequin R, Badeau R (2015) Singing voice detection with deep recurrent neural networks. In: Proceeding of IEEE international conference on acoustics, speech and signal processing (ICASSP). Brisbane, Australia, pp 121–125Google Scholar
  2. 2.
    Kim YE, Whitman B (2002) Singer identification in popular music recordings using voice coding features. In: Proceedings of the 3rd international conference on music information retrieval. Paris, France, pp 13–17Google Scholar
  3. 3.
    Salamon J, Gómez E (2012) Melody extraction from polyphonic music signals using pitch contour characteristics. IEEE Trans Audio Speech Lang Process 20(6):1759–1770CrossRefGoogle Scholar
  4. 4.
    Leglaive S, Hennequin R, Badeau R (2015) Singing voice detection with deep recurrent neural networks. In: Proceeding of IEEE international conference on acoustics, speech and signal processing (ICASSP). Brisbane, Australia, pp 121–125Google Scholar
  5. 5.
    Ono N, Miyamoto K, Le Roux J, Kameoka H, Sagayama S (2008) Separation of a monaural audio signal into harmonic/percussive components by complementary diffusion on spectrogram. In: Proceeding of 16th European signal processing conference. Lausanne, SwitzerlandGoogle Scholar
  6. 6.
    Jansson A, Humphrey E, Montecchio N, Bittner R, Kumar A, Weyde T (2017) Singing voice separation with deep U-Net convolutional networks. In: Proceeding of 18th international society for music information retrieval conference. Suzhou, ChinaGoogle Scholar
  7. 7.
    Sonnleitner R, Niedermayer B, Widmer G, Schlüter J (2012) A simple and effective spectral feature for speech detection in mixed audio signals. In: Proceedings of the 15th international conference on digital audio effects (DAFx’12). York, UKGoogle Scholar
  8. 8.
    Vembu S, Baumann S (2005) Separation of vocals from polyphonic audio recordings. In: Proceeding of international society for music information retrieval conference, London, UK, pp 337–344Google Scholar
  9. 9.
    Ramona M, Richard G, David B (2008) Vocal detection in music with support vector machines. In: Proceeding of IEEE international conference on acoustics, speech and signal processing (ICASSP). Las Vegas, USA, pp 1885–1888Google Scholar
  10. 10.
    Lehner B, Sonnleitner R, Widmer G (2013) Towards light-weight, real-time-capable singing voice detection. In: Proceeding of international society for music information retrieval conference. Curitiba, Brazil, pp 53–58Google Scholar
  11. 11.
    Lehner B, Widmer G, Sonnleitner, R (2014) On the reduction of false positives in singing voice detection. In: Proceeding of IEEE international conference on acoustics, speech and signal processing. Florence, Italy, pp 7480–7484Google Scholar
  12. 12.
    Regnier L, Peeters G (2009) Singing voice detection in music tracks using direct voice vibrato detection. In: Proceeding of IEEE international conference on acoustics, speech and signal processing. Taipei, Taiwan, pp 1685–1688Google Scholar
  13. 13.
    Pikrakis A, Kopsinis Y, Kroher N, Díaz-Báñez JM (2016) Unsupervised singing voice detection using dictionary learning. In: Proceeding of 24th European signal processing conference. Budapest, Hungary, pp 1212–1216Google Scholar
  14. 14.
    Lehner B, Widmer G, Bock S (2015) A low-latency, real-time-capable singing voice detection method with LSTM recurrent neural networks. In Proceeding of 23rd European signal processing conference. Nice, France, pp 21–25Google Scholar
  15. 15.
    Ellis DPW, Poliner GE (2007) Identifying cover songs’ with chroma features and dynamic programming beat tracking. In: Proceeding of IEEE international conference on acoustics, speech and signal processing. Honolulu, USA, pp 1429–1432Google Scholar
  16. 16.
    Chung J, Gulcehre C, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint, 1412.3555Google Scholar
  17. 17.
    Rocamora M, Herrera P (2017) Comparing audio descriptors for singing voice detection in music audio files. In: 11th Brazilian symposium on computer music. São Paulo, Brazil, pp 27–36Google Scholar
  18. 18.
    Mauch M, Fujihara H, Yoshii K, Goto M (2011) Timbre and melody features for the recognition of vocal activity and instrumental solos in polyphonic music. In: Proceeding of international society for music information retrieval conference. Miami, Florida, pp 233–238Google Scholar
  19. 19.
    Eyben F, Weninger F, Squartini S, Schuller B (2013) Real-life voice activity detection with LSTM recurrent neural networks and an application to hollywood movies. In: Proceeding of IEEE international conference on acoustics, speech and signal processing. Vancouver, Canada, pp 483–487Google Scholar
  20. 20.
    Schlüter J, Grill T (2015) Exploring data augmentation for improved singing voice detection with neural networks. In: Proceeding of international society for music information retrieval conference. Malaga, Spain, pp 121–126Google Scholar
  21. 21.
    Chan TS, Yeh TC, Fan ZC, Chen HW, Su L, Yang YH, Jang R (2015) Vocal activity informed singing voice separation with the iKala dataset. In: Proceeding of 2015 IEEE international conference on acoustics, speech and signal processing. Brisbane, Australia, pp 718–722Google Scholar
  22. 22.
    Bittner RM, Salamon J, Tierney M, Mauch M, Cannam C, Bello JP (2014) MedleyDB: a multitrack dataset for annotation-intensive MIR research. In: Proceeding of international society for music information retrieval conference, vol 14. Taipei, Taiwan, pp 155–160Google Scholar
  23. 23.
    Gupta H, Gupta D (2016) LPC and LPCC method of feature extraction in speech recognition system. In: Proceeding of 6th international conference cloud system and big data engineering. Noida, India, pp 498–502Google Scholar
  24. 24.
    Muller M, Ewert S, Kreuzer S (2009) Making chroma features more robust to timbre changes. In: Proceeding of IEEE international conference on acoustics, speech and signal processing. Taipei, Taiwan, pp 1877–1880Google Scholar
  25. 25.
    Leglaive S, Hennequin R, Badeau R (2015) Singing voice detection with deep recurrent neural networks. In: Proceeding of IEEE international conference on acoustics, speech and signal processing (ICASSP). Brisbane, Australia, pp 121–125Google Scholar
  26. 26.
    Sokolova M, Lapalme G (2009) A systematic analysis of performance measures for classification tasks. Inf Process Manage 45(4):427–437CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Zhigao Chen
    • 1
  • Xulong Zhang
    • 1
  • Jin Deng
    • 1
  • Juanjuan Li
    • 1
  • Yiliang Jiang
    • 1
  • Wei Li
    • 1
    • 2
    Email author
  1. 1.Department of Computer ScienceFudan UniversityShanghaiChina
  2. 2.Shanghai Key Laboratory of Intelligent Information ProcessingFudan UniversityShanghaiChina

Personalised recommendations