Models of Sound Localization

Colburn, H. Steven; Kulkarni, Abhijit

doi:10.1007/0-387-28863-5_8

Cited by 29 publications

(16 citation statements)

References 121 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A number of systems have taken a similar approach [6]- [10]. Localization in azimuth is a popular cue for segregating sound sources [11]. Spectral masking, sometimes called time-frequency masking, binary masking, or ideal binary masking, allows the separation of an arbitrary number of sources from a mixture, by assuming that a single source is active at every time-frequency point.…”

Section: A Backgroundmentioning

confidence: 99%

See 1 more Smart Citation

Model-Based Expectation-Maximization Source Separation and Localization

Mandel

Weiss

Ellis

2010

IEEE Trans. Audio Speech Lang. Process.

263

422

View full text Add to dashboard Cite

Abstract-This paper describes a system, referred to as 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 PESQ results 0.27 mean opinion score units greater than four comparable algorithms.

show abstract

Section: A Backgroundmentioning

confidence: 99%

“…Many models of mammalian auditory localization have been described in the literature, see [11] for a review. Most focus on localization within individual critical bands of the auditory system and are either based on cross-correlation [14] or the equalization-cancellation model [15], [16].…”

Section: A Backgroundmentioning

confidence: 99%

Model-Based Expectation-Maximization Source Separation and Localization

Mandel

Weiss

Ellis

2010

IEEE Trans. Audio Speech Lang. Process.

263

422

View full text Add to dashboard Cite

show abstract

“…Most acoustic cue-based approaches are limited to specific computational strategies that use exclusively the head related transfer functions (HRTFs), i.e. the direction-specific acoustic filtering by the pinnae and the head (Colburn & Kulkarni, 2005). Standard modeling approaches rely on acoustic information alone, and so cannot explain the effects of motor actions and other sensory modalities on the computation.…”

Section: Introductionmentioning

confidence: 99%

A Sensorimotor Approach to Sound Localization

2008

View full text Add to dashboard Cite

Sound localization is known to be a complex phenomenon, combining multisensory information processing, experience-dependent plasticity and movement. Here we present a sensorimotor model that addresses the question of how an organism could learn to localize sound sources without any a priori neural representation of its head related transfer function (HRTF) or prior experience with auditory spatial information. We demonstrate quantitatively that the experience of the sensory consequences of its voluntary motor actions allows an organism to learn the spatial location of any sound source. Using examples from humans and echolocating bats, our model shows that a naive organism can learn the auditory space based solely on acoustic inputs and their relation to motor states.

show abstract

“…[2]). Processing motivated by human binaural perception, which utilizes spatial cues including interaural time difference (ITD) and interaural intensity difference (IID) [3,4,5], has long been thought to be useful for separating sound sources from different directions and for coping with the effects of reverberation, and this approach is now being extended to speech recognition (e.g. [6]).…”

Section: Introductionmentioning

confidence: 99%

Missing Feature Speech Recognition using Dereverberation and Echo Suppression in Reverberant Environments

Park

Stern

2007

2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07

View full text Add to dashboard Cite

This paper describes an algorithm that efficiently segregates desired speech features from spatially-separated interfering sources in reverberant environments. Although most binaural segregation techniques successfully remove interference components in the absence of reverberation, source segregation in reverberant environments remains a challenging problem. In order to reduce the effects of reverberation, we present a method that dereverberates input signals before they are segregated. The dereverberation filter is estimated from the autocorrelation of the observations and primarily deals with early reflections, while late reflections are effectively suppressed by an inhibitory mechanism that estimates their relative contribution in each time-frequency segment. Information about the salience of the target in a given time-frequency segment based on source separation is combined with the corresponding information based on reverberation suppression through the use of a continually-variable weighting function or mask. Use of the novel reverberation processing results in a relative decrease in WER of 11.5% to 20.9% and use of the combined approaches reduces relative WER by as much as 65.3%.

show abstract

Models of Sound Localization

Cited by 29 publications

References 121 publications

Model-Based Expectation-Maximization Source Separation and Localization

Model-Based Expectation-Maximization Source Separation and Localization

A Sensorimotor Approach to Sound Localization

Missing Feature Speech Recognition using Dereverberation and Echo Suppression in Reverberant Environments

Contact Info

Product

Resources

About