http://iet.metastore.ingenta.com
1887

access icon openaccess Expectation-maximisation for speech source separation using convolutive transfer function

This is an open access article published by the IET, Chinese Association for Artificial Intelligence and Chongqing University of Technology under the Creative Commons Attribution -NonCommercial License (http://creativecommons.org/licenses/by-nc/3.0/)
Received 22/11/2018, Accepted 13/01/2019, Revised 09/01/2019, Published 14/01/2019
Loading full text...

Full text loading...

/deliver/fulltext/trit/4/1/TRIT.2018.1061.html;jsessionid=fwld3339c6vs.x-iet-live-01?itemId=%2fcontent%2fjournals%2f10.1049%2ftrit.2018.1061&mimeType=html&fmt=ahah

Inspec keywords: expectation-maximisation algorithm; speech processing; microphone arrays; Fourier transforms; blind source separation; reverberation; transfer functions; convolution; microphones; speech enhancement; source separation; frequency-domain analysis

Other keywords: CTF coefficients; under-determined speech source separation; mixing filters; multichannel microphone signals; room filters; expectation-maximisation algorithm; multiple sources; convolutive transfer function; STFT coefficients; STFT domain; convolutive mixtures; time-domain signals; (STFT) domain; short-time Fourier; widely used narrowband assumption

Subjects: Other topics in statistics; Speech processing techniques; Other topics in statistics; Speech and audio signal processing; Signal processing and detection

http://iet.metastore.ingenta.com/content/journals/10.1049/trit.2018.1061
Loading

Related content

content/journals/10.1049/trit.2018.1061
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address