Two-microphone Separation of Speech Mixtures

Michael Syskind Pedersen; DeLiang Wang; Jan Larsen; Ulrik Kjems

Two-microphone Separation of Speech Mixtures

Michael Syskind Pedersen (Author), DeLiang Wang (Author), Jan Larsen (Author), Ulrik Kjems (Author)

Research output: Non-textual form › Interactive production › Research

Abstract

In this demonstration we show the separation of 3-7 mixed speech sources based on information from two microphones. Separation with background noise is demonstrated too. The algorithms are described in 1] Michael Syskind Pedersen, DeLiang Wang, Jan Larsen and Ulrik Kjems: "Two-microphone Separation of Speech Mixtures," 2006, submited for journal publication. See also, [2] Michael Syskind Pedersen, DeLiang Wang, Jan Larsen and Ulrik Kjems: "Overcomplete Blind Source Separation by Combining ICA and Binary Time-Frequency Masking," in proceedings of IEEE International workshop on Machine Learning for Signal Processing, pp. 15-20, 2005.

Original language	English
Publication date	2006
Publication status	Published - 2006

Keywords

Underdetermined ICA

Access to Document

http://www.imm.dtu.dk/pubdb/p.php?4399

OpenUrl availability

Full text

Cite this

@misc{aa9b57dbc7db4f188982591c69d8ad15,

title = "Two-microphone Separation of Speech Mixtures",

abstract = "In this demonstration we show the separation of 3-7 mixed speech sources based on information from two microphones. Separation with background noise is demonstrated too. The algorithms are described in 1] Michael Syskind Pedersen, DeLiang Wang, Jan Larsen and Ulrik Kjems: {"}Two-microphone Separation of Speech Mixtures,{"} 2006, submited for journal publication. See also, [2] Michael Syskind Pedersen, DeLiang Wang, Jan Larsen and Ulrik Kjems: {"}Overcomplete Blind Source Separation by Combining ICA and Binary Time-Frequency Masking,{"} in proceedings of IEEE International workshop on Machine Learning for Signal Processing, pp. 15-20, 2005.",

keywords = "Underdetermined ICA",

author = "Pedersen, {Michael Syskind} and DeLiang Wang and Jan Larsen and Ulrik Kjems",

year = "2006",

language = "English",

publisher = "IMM",

}

TY - ADVS

T1 - Two-microphone Separation of Speech Mixtures

A2 - Pedersen, Michael Syskind

A2 - Wang, DeLiang

A2 - Larsen, Jan

A2 - Kjems, Ulrik

PY - 2006

Y1 - 2006

N2 - In this demonstration we show the separation of 3-7 mixed speech sources based on information from two microphones. Separation with background noise is demonstrated too. The algorithms are described in 1] Michael Syskind Pedersen, DeLiang Wang, Jan Larsen and Ulrik Kjems: "Two-microphone Separation of Speech Mixtures," 2006, submited for journal publication. See also, [2] Michael Syskind Pedersen, DeLiang Wang, Jan Larsen and Ulrik Kjems: "Overcomplete Blind Source Separation by Combining ICA and Binary Time-Frequency Masking," in proceedings of IEEE International workshop on Machine Learning for Signal Processing, pp. 15-20, 2005.

AB - In this demonstration we show the separation of 3-7 mixed speech sources based on information from two microphones. Separation with background noise is demonstrated too. The algorithms are described in 1] Michael Syskind Pedersen, DeLiang Wang, Jan Larsen and Ulrik Kjems: "Two-microphone Separation of Speech Mixtures," 2006, submited for journal publication. See also, [2] Michael Syskind Pedersen, DeLiang Wang, Jan Larsen and Ulrik Kjems: "Overcomplete Blind Source Separation by Combining ICA and Binary Time-Frequency Masking," in proceedings of IEEE International workshop on Machine Learning for Signal Processing, pp. 15-20, 2005.

KW - Underdetermined ICA

M3 - Interactive production

PB - IMM

ER -

Two-microphone Separation of Speech Mixtures

Abstract

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this