Expectation‐maximisation for speech source separation using convolutive transfer function. Issue 1 (18th February 2019)

• Record Type: Journal Article
• Authors: Li, Xiaofei; Girin, Laurent; Horaud, Radu
• Is Part Of: CAAI transactions on intelligence technology. Volume 4:Issue 1(2019)
• Page Start: 47
• Page End: 53
• Publication Date: 2019-02-18
• Subjects: speech enhancement -- expectation‐maximisation algorithm -- transfer functions -- speech processing -- Fourier transforms -- microphone arrays -- frequency‐domain analysis -- blind source separation -- microphones -- convolution -- source separation -- reverberation; convolutive transfer function -- under‐determined speech source separation -- multichannel microphone signals -- convolutive mixtures -- multiple sources -- time‐domain signals -- short‐time Fourier -- (STFT) domain -- room filters -- STFT domain -- widely used narrowband assumption -- CTF coefficients -- mixing filters -- STFT coefficients -- expectation‐maximisation algorithm; B0240Z Other topics in statistics -- B6130 Speech and audio signal processing -- B6140 Signal processing and detection -- C1140Z Other topics in statistics -- C5260S Speech processing techniques; Artificial intelligence -- Periodicals; Computer science -- Periodicals; Artificial intelligence; Computer science; Electronic journals; Periodicals; 006.305
• DOI: 10.1049/trit.2018.1061
• Languages: English
• ISSNs: 2468-6557

Abstract

Abstract : This study addresses the problem of under‐determined speech source separation from multichannel microphone signals, i.e. the convolutive mixtures of multiple sources. The time‐domain signals are first transformed to the short‐time Fourier transform (STFT) domain. To represent the room filters in the STFT domain, instead of the widely used narrowband assumption, the authors propose to use a more accurate model, i.e. the convolutive transfer function (CTF). At each frequency band, the CTF coefficients of the mixing filters and the STFT coefficients of the sources are jointly estimated by maximising the likelihood of the microphone signals, which is resolved by an expectation‐maximisation algorithm. Experiments show that the proposed method provides very satisfactory performance under highly reverberant environments.