ICA와 DNN을 이용한 방송 드라마 콘텐츠에서 음악구간 검출 성능
Performance of music section detection in broadcast drama contents using independent component analysis and deep neural networks
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
We propose to use independent component analysis (ICA) and deep neural network (DNN) to detect music sections in broadcast drama contents. Drama contents mainly comprise silence, noise, speech, music, and mixed (speech+music) sections. The silence section is detected by signal activity detection. To detect the music section, we train noise, speech, music, and mixed models with DNN. In computer experiments, we used the MUSAN corpus for training the acoustic model, and conducted an experiment using 3 hours’ worth of Korean drama contents. As the mixed section includes music signals, it was regarded as a music section. The segmentation error rate (SER) of music section detection was observed to be 19.0%. In addition, when stereo mixed signals were separated into music signals using ICA, the SER was reduced to 11.8%.
Abstract
We propose to use independent component analysis (ICA) and deep neural network (DNN) to detect music sections in broadcast drama contents. Drama contents mainly comprise silence, noise, speech, music, and mixed (speech+music) sections. The silence section is detected by signal activity detection. To detect the music section, we train noise, speech, music, and mixed models with DNN. In computer experiments, we used the MUSAN corpus for training the acoustic model, and conducted an experiment using 3 hours’ worth of Korean drama contents. As the mixed section includes music signals, it was regarded as a music section. The segmentation error rate (SER) of music section detection was observed to be 19.0%. In addition, when stereo mixed signals were separated into music signals using ICA, the SER was reduced to 11.8%.
참고문헌 (23)
- Aguilo, M., "A hierarchical architecture for audio segmentation in a broadcast news task", Proceedings of I Iberian SLTech, pp.17~20 (2009)
- Boersma, P., "Praat, a system for doing phonetics by computer", Glot International, 5(9-10), pp.341~345 (2001)
- Castán, D., "Albayzín-2014 evaluation: Audio segmentation and classification in broadcast news domains", EURASIP Journal on Audio, Speech, and Music Processing, 2015(1), pp.33~ (2015)
- Galibert, O., "Methodologies for the evaluation of speaker diarization and automatic speech recognition in the presence of overlapping speech", Proceedings of INTERSPEECH-2013, pp.1131~1134 (2013)
- Gallardo-Antolín, A., "UPM-UC3M system for music and speech segmentation", Proceedings of VI Jornadas en Tecnología del Habla II Iberian SLTech Workshop (FALA), pp.421~424 (2010)
- Gallardo-Antolín, A., "Histogram equalizationbased features for speech, music and song discrimination", IEEE Signal Processing Letters, 17(7), pp.659~662 (2010)
- Gupta, V., "I-vector based speaker adaptation of deep neural networks for French broadcast audio transcription", Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp.6334~6338 (2014)
- Heittola, T., "Sound event detection in multisource environments using source separation", Proceedings of Workshop Machine Listening in Multisource Environments, pp.36~40 (2011)
- Hinton, G., "Deep neural networks for acoustic modeling in speech recognition", IEEE Signal Processing Magazine, 29(6), pp.82~97 (2012)
- Hyvärinen, A., "Fast and robust fixed-point algorithms for independent component analysis", Neural Networks, 10(3), pp.626~634 (1999)
- Hyvärinen, A., "Independent component analysis:Algorithms and applications", Neural Networks, 13(4-5), pp.411~430 (2000)
- Justusson, B. I., "Two-Dimensional Digital Signal Processing II", pp.161~196 (1981), Springer
- 이규호, "지상파 방송사의 음악저작물 방송사용료의적정성에 대한 연구", 음악콘텐츠와 법, pp.203~250 (2015)
- Metallinou, A., "Audio-visual emotion recognition using Gaussian mixture models for face and voice", Proceedings of International Symposium on Multimedia (ISM), pp.250~257 (2008)
- Mirsa, H., "Spectral entropy based feature for robust ASR", Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp.193~196 (2004)
- Müller, M., "Chroma toolbox: MATLAB implementations for extracting variants of chroma-based audio features", Proceedings of International Society for Music Information Retrieval Conference (ISMIR), pp.215~220 (2011)
- Povey, D., "The Kaldi speech recognition toolkit", Proceedings of IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) (2011)
- Saon, G., "Speaker adaptation of neural network acoustic models using i-vectors", Proceedings of IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp.55~59 (2013)
- "SBS drama special: Mask" (2015)[URL]
- "Musan: A music, speech, and noise corpus" (2015)[URL]
- Srivastava, N., "Dropout : A simple way to prevent neural networks from overfitting", The Journal of Machine Learning Research, 15(1), pp.1929~1958 (2014)
- van der Maaten, L., "Visualizing data using t-SNE", The Journal of Machine Learning Research, 9(1), pp.2579~2605 (2008)
- Wang, S. S., "Acoustic feature conversion using a polynomial based feature transferring algorithm", Proceedings of International Symposium on Chinese Spoken Language Processing (ISCSLP), pp.454~458 (2014)