Model-Based Expectation-Maximization Source Separation and Localization

This paper describes a system, referred to as model-based expectation-maximization source separation and localization (MESSL), for separating and localizing multiple sound sources from an underdetermined reverberant two-channel recording. By clustering individual spectrogram points based on their in...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on audio, speech, and language processing Ročník 18; číslo 2; s. 382 - 394
Hlavní autoři: Mandel, M.I., Weiss, R.J., Ellis, D.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway, NJ IEEE 01.02.2010
Institute of Electrical and Electronics Engineers
Témata:
Applied sciences
Background noise
Delay
Detection, estimation, filtering, equalization, prediction
Digital recording
Exact sciences and technology
Expectation-maximization algorithms
Information, signal and communications theory
Iterative algorithms
Maximum-likelihood estimation
Miscellaneous
Parameter estimation
Predictive models
Signal and communications theory
Signal processing
Signal representation. Spectral analysis
Signal, noise
Source separation
Spectrogram
Speech enhancement
Speech processing
Telecommunications and information theory
time-frequency masking
underdetermined source separation
Automatic classification
Parameter estimation
Source separation
Signal estimation
Mixture theory
Sound quality
Spectrum analysis
Speech enhancement
time-frequency masking
Masking
Delay time
Target detection
Probabilistic approach
Two channel system
Maximum-likelihood estimation
Sound source
Signal classification
Source localization
Signal processing
underdetermined source separation
Phase delay
Maximum likelihood
EM algorithm
Signal analysis
Speech processing
Signal distortion
ISSN:1558-7916
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This paper describes a system, referred to as model-based expectation-maximization source separation and localization (MESSL), for separating and localizing multiple sound sources from an underdetermined reverberant two-channel recording. By clustering individual spectrogram points based on their interaural phase and level differences, MESSL generates masks that can be used to isolate individual sound sources. We first describe a probabilistic model of interaural parameters that can be evaluated at individual spectrogram points. By creating a mixture of these models over sources and delays, the multi-source localization problem is reduced to a collection of single source problems. We derive an expectation-maximization algorithm for computing the maximum-likelihood parameters of this mixture model, and show that these parameters correspond well with interaural parameters measured in isolation. As a byproduct of fitting this mixture model, the algorithm creates probabilistic spectrogram masks that can be used for source separation. In simulated anechoic and reverberant environments, separations using MESSL produced on average a signal-to-distortion ratio 1.6 dB greater and perceptual evaluation of speech quality (PESQ) results 0.27 mean opinion score units greater than four comparable algorithms.
Bibliografie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:1558-7916
DOI:10.1109/TASL.2009.2029711