Terry Tan
ABSTRACT
This paper aims to evaluate singing performance based on deep metric learning. As the vocal sound will be the input, we will first need to separate that from a soundtrack. After the separation, the vocal audio will be represented by Mel-spectrogram as an input in our proposed model. The process to build up our model splits into pre-training and training steps. Meta learning is adopted for pre-training while deep metric learning is adopted for training. The output of the model is a Euclidean distance reflecting the singers' performance, which is determined by comparing their sounds to the originals. Experimental results show a stable and reliable singing evaluation.
- Goto, Masataka. "Singing information processing." 2014 12th International Conference on Signal Processing (ICSP). IEEE, 2014.Google Scholar
- He K, et al. "Deep residual learning for image recognition." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.Google Scholar
- Hoffer, Elad, and Nir Ailon. "Deep metric learning using triplet network." International Workshop on Similarity-Based Pattern Recognition. Springer, Cham, 2015.Google Scholar
- Kingma, D. P., and Jimmy Ba. "Adam: A method for stochastic optimization." arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- Lin, Chang-Hung, et al. "Automatic singing evaluating system based on acoustic features and rhythm." 2014 International Conference on Orange Technologies. IEEE, 2014.Google Scholar
- Maka, Tomasz. "Attributes of audio feature contours for automatic singing evaluation." 2013 36th International Conference on Telecommunications and Signal Processing (TSP). IEEE, 2013.Google Scholar
- Rafii, Zafar, and Bryan Pardo. "Repeating pattern extraction technique (REPET): A simple method for music/voice separation." IEEE transactions on audio, speech, and language processing 21.1 (2013): 73--84.Google Scholar
- Sung, Flood, et al. "Learning to compare: Relation network for few-shot learning." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.Google Scholar
- Schroff, Florian, Dmitry Kalenichenko, and James Philbin. "Facenet: A unified embedding for face recognition and clustering." Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.Google Scholar
- Tsai, Wei-Ho, and Hsin-Chieh Lee. "Automatic evaluation of karaoke singing based on pitch, volume, and rhythm features." IEEE Transactions on Audio, Speech, and Language Processing 20.4 (2012): 1233--1243.Google ScholarDigital Library
- Vijayan, Karthika, Xiaoxue Gao, and Haizhou Li. "Analysis of speech and singing signals for temporal alignment." 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). IEEE, 2018.Google Scholar
- Wang, Chung-Che, and Jyh-Shing Roger Jang. "Improving query-by-singing/humming by combining melody and lyric information." IEEE/ACM Transactions on Audio, Speech, and Language Processing 23.4 (2015): 798--806.Google ScholarDigital Library
- Yu, Yang, et al. "Performance scoring of singing voice." 2015 International Conference on Asian Language Processing (IALP). IEEE, 2015.Google Scholar
- Zhang, Ning, et al. "Automatic Singing Evaluation without Reference Melody Using Bi-dense Neural Network." ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2019.Google Scholar
- Zheng, Jiewen, Qingli Ma, and Wuyang Zhou. "Performance comparison of full-batch bp and mini-batch bp algorithm on spark framework." 2016 8th International Conference on Wireless Communications & Signal Processing (WCSP). IEEE, 2016.Google Scholar
Index Terms
- Singing Evaluation based on Deep Metric Learning
Recommendations
Deep Metric Learning for Sequential Data Using Approximate Information
Machine Learning and Data Mining in Pattern RecognitionAbstractLearning a distance metric provides solutions to many problems where the data exists in a high dimensional space and hand-crafted distance metrics fail to capture its semantical structure. Methods based on deep neural networks such as Siamese or ...
Creating an A Cappella Singing Audio Dataset for Automatic Jingju Singing Evaluation Research
DLfM '17: Proceedings of the 4th International Workshop on Digital Libraries for MusicologyThe data-driven computational research on automatic jingju (also known as Beijing or Peking opera) singing evaluation lacks a suitable and comprehensive a cappella singing audio dataset. In this work, we present an a cappella singing audio dataset which ...
Attention-Based Ensemble for Deep Metric Learning
Computer Vision – ECCV 2018AbstractDeep metric learning aims to learn an embedding function, modeled as deep neural network. This embedding function usually puts semantically similar images close while dissimilar images far from each other in the learned embedding space. Recently, ...
Comments