Fast Monaural Separation of Speech

Pontoppidan NH, Dyrholm M. Fast Monaural Separation of Speech. In: AES Conference: 23rd International Conference: Signal Processing in Audio Recording and Reproduction. Audio Engineering Society; 2003. Paper 6. Available from: https://aes.org/publications/elibrary-page/?id=12331

@inproceedings{Pontoppidan2003_12331,
  author = {Pontoppidan, Niels H. and Dyrholm, Mads},
  title = {{Fast Monaural Separation of Speech}},
  booktitle = {AES Conference: 23rd International Conference: Signal Processing in Audio Recording and Reproduction},
  note = {Paper 6},
  year = {2003},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=12331}
}

TY  - CPAPER
TI  - Fast Monaural Separation of Speech
AU  - Pontoppidan, Niels H.
AU  - Dyrholm, Mads
T2  - AES Conference: 23rd International Conference: Signal Processing in Audio Recording and Reproduction
M1  - Paper 6
PY  - 2003
DA  - 2003/05/06
UR  - https://aes.org/publications/elibrary-page/?id=12331
PB  - Audio Engineering Society
LA  - en
AB  - We have investigated the possibility of separating signals from a single mixture of sources. This problem is termed the Monaural Separation Problem. Lars Kai Hansen has argued that this problem is topological tougher than problems with multiple recordings. Roweis has shown that inference from a Factorial Hidden Markov Model, with non-stationary assumptions on the source autocorrelations modelled through the Factorial Hidden Markov Model, leads to separation in the monaural case. By extending Hansens work we find that Roweis' assumptions are necessary for monaural speech separation. Furthermore we develop a Factorial hierarchical vector quantizer yielding a significant decrease in complexity of inference.
ER  -