Multi-stage coherence drift based sampling rate synchronization for acoustic beamforming

Schmalenstroeer, Joerg; Heymann, Jahn; Drude, Lukas; Boeddecker, Christoph; Haeb‐Umbach, Reinhold

doi:10.1109/mmsp.2017.8122278

Cited by 27 publications

(38 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One way to solve this is to enforce a zerophase-sum constraint [81,Equation 2.13]. An alternative is to arbitrarily set the phase of a reference channel to zero [149,Equation 21] or to minimize the group delay introduced by the filter [149,Equation 22]. For a comparison of phase corrections, please again refer to [137].…”

Section: Magnitude and Phase Normalization Of Beamforming Vectorsmentioning

confidence: 99%

See 1 more Smart Citation

Integration of Neural Networks and Probabilistic Spatial Models for Acoustic Blind Source Separation

Drude

Haeb‐Umbach

2019

IEEE J. Sel. Top. Signal Process.

Self Cite

View full text Add to dashboard Cite

Despite a lot of progress in speech separation, enhancement, and automatic speech recognition realistic meeting recognition is still fairly unsolved. Most research on speech separation either focuses on spectral cues to address single-channel recordings or spatial cues to separate multichannel recordings and exclusively either rely on neural networks or probabilistic graphical models. Integrating a spatial clustering approach and a deep learning approach using spectral cues in a single framework can significantly improve automatic speech recognition performance and improve generalizability given that a neural network profits from a vast amount of training data while the probabilistic counterpart adapts to the current scene. This thesis at hand, therefore, concentrates on the integration of two fairly disjoint research streams, namely single-channel deep learning-based source separation and multi-channel probabilistic modelbased source separation. It provides a general framework to integrate spatial and spectral cues in which neural networks and probabilistic graphical models complement each other in achieving state of the art performance in blind source separation on noisy, reverberant data. The efficacy of the proposed approaches is evaluated on simulated artificial mixtures as well as real recordings of simultaneously active speakers. The key findings are (1) a cascade integration in which a neural network initializes a probabilistic graphical model provides substantial improvement, (2) spatial cues can be used for unsupervised training of neural networks, (3) tight integration, an integration in which a joint agreement between both modalities and models is found, leads to lowest word error rates and best generalizability to unseen real mixtures.

show abstract

Section: Magnitude and Phase Normalization Of Beamforming Vectorsmentioning

confidence: 99%

“…This indicates that it is well worth investigating further how the absolute phase should be determined. Initial results on phase normalization for GEV beamforming vectors can be found in [149,Section V].…”

Section: Source Extractionmentioning

confidence: 99%

Integration of Neural Networks and Probabilistic Spatial Models for Acoustic Blind Source Separation

Drude

Haeb‐Umbach

2019

IEEE J. Sel. Top. Signal Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…When mapping a link (p 1 , p 2 ) with p 1 hosted on v 1 , and trying to find a node v 2 to host p 2 , we only look at the k neighbors of v 1 with best attenuation values. Figure 6: Overlay graph from acoustic signal processing [12] with a loop from block 5 to 2 5. Evaluation…”

Section: Limit Tree Degreementioning

confidence: 99%

“…We choose a generic algorithm from the field of acoustic signal processing for our overlay graph [12]. Figure 6 depicts the graph with 5 processing blocks equally weighted w p = w o .…”

Section: Scenariomentioning

confidence: 99%

MARVELO: Wireless virtual network embedding for overlay graphs with loops

Afifi

Auroux

Karl

2018

2018 IEEE Wireless Communications and Networking Conference (WCNC)

View full text Add to dashboard Cite

When deploying resource-intensive signal processing applications in wireless sensor or mesh networks, distributing processing blocks over multiple nodes becomes promising. Such distributed applications need to solve the placement problem (which block to run on which node), the routing problem (which link between blocks to map on which path between nodes), and the scheduling problem (which transmission is active when). We investigate a variant where the application graph may contain feedback loops and we exploit wireless networks' inherent multicast advantage. Thus, we propose Multicast-Aware Routing for Virtual network Embedding with Loops in Overlays (MARVELO) to find efficient solutions for scheduling and routing under a detailed interference model. We cast this as a mixed integer quadratically constrained optimisation problem and provide an efficient heuristic. Simulations show that our approach handles complex scenarios quickly.• We support overlay graphs with loops, as often found in signal processing applications. • We leverage the wireless multicast advantage as typical signal processing applications sending the same data to multiple receivers (e.g., in loops). • When scheduling wireless transmission, we consider interference from all sending nodes.

show abstract

“…More specifically, a so-called multi-stage (i.e., offline CL) procedure estimates SRO/STO across the whole sensor signal and resamples it and reiterates, which rests upon the observation that SRO estimation bias vanishes with smaller input SRO. Any OL estimator of SRO/STO can be embedded into a multi-stage (MS) form as shown in [15] for the estimator in [13]. While the basic MS procedure is conceived in [16], a two-stage scheme is proposed in [19].…”

Section: Introduction and Relation To Prior Workmentioning

confidence: 99%

Control Architecture of the Double-Cross-Correlation Processor for Sampling-Rate-Offset Estimation in Acoustic Sensor Networks

Chinaev

Wienand

Enzner

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Distributed hardware of acoustic sensor networks bears inconsistency of local sampling frequencies, which is detrimental to signal processing. Fundamentally, sampling rate offset (SRO) nonlinearly relates the discrete-time signals acquired by different sensor nodes. As such, retrieval of SRO from the available signals requires nonlinear estimation, like double-cross-correlation processing (DXCP), and frequently results in biased estimation. SRO compensation by asynchronous sampling rate conversion (ASRC) on the signals then leaves an unacceptable residual. As a remedy to this problem, multistage procedures have been devised to diminish the SRO residual with multiple iterations of SRO estimation and ASRC over the entire signal. This paper converts the mechanism of offline multi-stage processing into a continuous feedback-control loop comprising a controlled ASRC unit followed by an online implementation of DXCPbased SRO estimation. To support the design of an optimum internal model control unit for this closed-loop system, the paper deploys an analytical dynamical model of the proposed online DXCP. The resulting control architecture then merely applies a single treatment of each signal frame, while efficiently diminishing SRO bias with time. Evaluations with both speech and Gaussian input demonstrate that the high accuracy of multi-stage processing is maintained at the low complexity of single-stage (open-loop) processing.

show abstract

Multi-stage coherence drift based sampling rate synchronization for acoustic beamforming

Cited by 27 publications

References 13 publications

Integration of Neural Networks and Probabilistic Spatial Models for Acoustic Blind Source Separation

Integration of Neural Networks and Probabilistic Spatial Models for Acoustic Blind Source Separation

MARVELO: Wireless virtual network embedding for overlay graphs with loops

Control Architecture of the Double-Cross-Correlation Processor for Sampling-Rate-Offset Estimation in Acoustic Sensor Networks

Contact Info

Product

Resources

About