A Study on Manifolds of Acoustic Responses

Laufer-Goldshtein, Bracha; Talmon, Ronen; Gannot, Sharon

doi:10.1007/978-3-319-22482-4_23

Cited by 26 publications

(35 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A clear correspondence is demonstrated, proving that the diffusion mapping indeed blindly extracts the intrinsic degree-of-freedom of the RTF set, and hence can be utilized for data-driven localization. 143 It is acknowledged that collecting labeled data in reverberant environment is a cumbersome task, however measuring RTFs in the enclosure is relatively easy. It is therefore proposed to collect a large number of RTFs in the room where localization is required.…”

Section: B Speaker Localization and Tracking Using Manifold Learningmentioning

confidence: 99%

Machine learning in acoustics: Theory and applications

Bianco

Gerstoft

Traer

et al. 2019

The Journal of the Acoustical Society of America

Self Cite

424

126

View full text Add to dashboard Cite

Acoustic data provide scientific and engineering insights in fields ranging from biology and communications to ocean and Earth science. We survey the recent advances and transformative potential of machine learning (ML), including deep learning, in the field of acoustics. ML is a broad family of statistical techniques for automatically detecting and utilizing patterns in data. Relative to conventional acoustics and signal processing, ML is data-driven. Given sufficient training data, ML can discover complex relationships between features and desired labels or actions, or between features themselves. With large volumes of training data, ML can discover models describing complex acoustic phenomena such as human speech and reverberation. ML in acoustics is rapidly developing with compelling results and significant future promise. We first introduce ML, then highlight ML developments in five acoustics research areas: source localization in speech processing, source localization in ocean acoustics, bioacoustics, seismic exploration, and environmental sounds in everyday scenes.

show abstract

Section: B Speaker Localization and Tracking Using Manifold Learningmentioning

confidence: 99%

Machine learning in acoustics: Theory and applications

Bianco

Gerstoft

Traer

et al. 2019

The Journal of the Acoustical Society of America

Self Cite

424

126

View full text Add to dashboard Cite

show abstract

“…The observation that the RTFs are controlled by a small set of parameters, such as room dimensions, reverberation time, location of the source and the sensors etc., gives rise to the assumption that they are confined to a low dimensional manifold. In [36] and [30], we have shown that the RTFs of a certain node have a distinct structure. Hence, they are not uniformly distributed in the entire space, but rather pertain to a manifold M m of much lower dimensions.…”

Section: Problem Formulationmentioning

confidence: 99%

Semi-Supervised Source Localization on Multiple Manifolds With Distributed Microphones

Laufer-Goldshtein

Talmon

Gannot

2017

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

The problem of source localization with ad hoc microphone networks in noisy and reverberant enclosures, given a training set of prerecorded measurements, is addressed in this paper. The training set is assumed to consist of a limited number of labelled measurements, attached with corresponding positions, and a larger amount of unlabelled measurements from unknown locations. However, microphone calibration is not required. We use a Bayesian inference approach for estimating a function that maps measurement-based feature vectors to the corresponding positions. The central issue is how to combine the information provided by the different microphones in a unified statistical framework. To address this challenge, we model this function using a Gaussian process with a covariance function that encapsulates both the connections between pairs of microphones and the relations among the samples in the training set. The parameters of the process are estimated by optimizing a maximum likelihood (ML) criterion. In addition, a recursive adaptation mechanism is derived where the new streaming measurements are used to update the model. Performance is demonstrated for 2-D localization of both simulated data and real-life recordings in a variety of reverberation and noise levels.

show abstract

“…To calculate (12), an estimate of the RTFs-matrix C(l, k) and the noise correlation matrix Φ vv are required.…”

Section: Linearly Constrained Minimum Variancementioning

confidence: 99%

“…The fact that we deal with low reverberation level makes the distance measure (19) a valid affinity measure between impulse responses (see discussion in [12].). Under the assumption that only one speaker is active, the position of the active speaker is determined by I(l):…”

Section: B Speaker Position Identification Based On Pre-trained Rtfsmentioning

confidence: 99%

Speaker extraction using LCMV beamformer with DNN-based SPP and RTF identification scheme

Ariel

Chazan

Malka

et al. 2017

2017 25th European Signal Processing Conference (EUSIPCO)

Self Cite

View full text Add to dashboard Cite

Abstract-The linearly constrained minimum variance (LCMV)-beamformer (BF) is a viable solution for desired source extraction from a mixture of speakers in a noisy environment. The performance in terms of speech distortion, interference cancellation and noise reduction depends on the estimation of a set of parameters. This paper presents a new mechanism to update the parameters of the LCMV-BF. A new speech presence probability (SPP)-based voice activity detector (VAD) controls the noise covariance matrix update, and a speaker position identifier (SPI) procedure controls the relative transfer functions (RTFs) update. A postfilter is then applied to the BF output to further attenuate the residual noise signal. A series of experiments using real-life recordings confirm the speech enhancement capabilities of the proposed algorithm.

show abstract

A Study on Manifolds of Acoustic Responses

Cited by 26 publications

References 8 publications

Machine learning in acoustics: Theory and applications

Machine learning in acoustics: Theory and applications

Semi-Supervised Source Localization on Multiple Manifolds With Distributed Microphones

Speaker extraction using LCMV beamformer with DNN-based SPP and RTF identification scheme

Contact Info

Product

Resources

About