Catalog-based single-channel speech-music separation
Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010, ss.2782-2785, 2010 (Scopus)
- Yayın Türü: Makale / Özet
- Basım Tarihi: 2010
- Dergi Adı: Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010
- Derginin Tarandığı İndeksler: Scopus
- Sayfa Sayıları: ss.2782-2785
- Anahtar Kelimeler: Mixture of Poissons, NMF, Single-channel, Speech-music separation
- Boğaziçi Üniversitesi Adresli: Evet
Özet
We propose a new catalog-based speech-music separation method for background music removal. Assuming that we know a catalog of the background music, we develop a generative model for the superposed speech and music spectrograms. We represent the speech spectrogram by a Non-negative Matrix Factorization (NMF) model and the music spectrogram by a conditional Poisson Mixture Model (PMM). By choosing the size of the catalog, i.e., the number of mixture components we can tradeoff speed versus accuracy. The combined hierarchical model leads to a mixture of multinomial distributions as the joint posterior of music and speech. Separation and hyper-parameter adaptation can be achieved via an Expectation Maximization algorithm. Experimental results show that separation performance of the algorithm is promising. Furthermore, we show that incorporating prior information such as volume adjustment parameter can enhance the separation performance. © 2010 ISCA.