DOA-estimation based on a complex Watson kernel method

Drude, Lukas; Jacob, Florian; Haeb‐Umbach, Reinhold

doi:10.1109/eusipco.2015.7362384

Cited by 8 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the calibration results are matched to the ground truth geometry by a rigid body transformation for evaluation. For DoA estimation, the complex Watson kernel method [19] is used.…”

Section: Geometry Calibrationmentioning

confidence: 99%

See 1 more Smart Citation

Deep Neural Network based Distance Estimation for Geometry Calibration in Acoustic Sensor Networks

Gburrek

Schmalenstroeer

Brendel

et al. 2021

2020 28th European Signal Processing Conference (EUSIPCO)

Self Cite

View full text Add to dashboard Cite

We present an approach to deep neural network based (DNN-based) distance estimation in reverberant rooms for supporting geometry calibration tasks in wireless acoustic sensor networks. Signal diffuseness information from acoustic signals is aggregated via the coherent-to-diffuse power ratio to obtain a distance-related feature, which is mapped to a sourceto-microphone distance estimate by means of a DNN. This information is then combined with direction-of-arrival estimates from compact microphone arrays to infer the geometry of the sensor network. Unlike many other approaches to geometry calibration, the proposed scheme does only require that the sampling clocks of the sensor nodes are roughly synchronized. In simulations we show that the proposed DNN-based distance estimator generalizes to unseen acoustic environments and that precise estimates of the sensor node positions are obtained.

show abstract

“…Thus, the calibration results are matched to the ground truth geometry by a rigid body transformation for evaluation. For DoA estimation, the complex Watson kernel method [19] is used.…”

Section: Geometry Calibrationmentioning

confidence: 99%

“…Noticeably, the MPE increases for larger T 60 values. This is caused by the degradation of the DoA estimates in more reverberant environments (see [19]). Additionally, the distance estimation errors influenced the calibration results only marginally.…”

Section: Geometry Calibrationmentioning

confidence: 99%

Deep Neural Network based Distance Estimation for Geometry Calibration in Acoustic Sensor Networks

Gburrek

Schmalenstroeer

Brendel

et al. 2021

2020 28th European Signal Processing Conference (EUSIPCO)

Self Cite

View full text Add to dashboard Cite

show abstract

“…τ k,m = d T k r m /c with d k the unit vector in the k-th coming direction, r m ∈ R 3 the coordinates of the m-th microphone, and c the sound velocity. The concentration parameter η k is decided through empirical analysis, and we set η k = 5 here, as suggested in [27], which means equal importance is put on different frequencies. For modeling the background noise, η k is set to zero, which leads to a uniform distribution.…”

Section: Weight Parameter Estimationmentioning

confidence: 99%

Target Speaker Localization Based on the Complex Watson Mixture Model and Time-Frequency Selection Neural Network

Wang

Yan

2018

Applied Sciences

View full text Add to dashboard Cite

Common sound source localization algorithms focus on localizing all the active sources in the environment. While the source identities are generally unknown, retrieving the location of a speaker of interest requires extra effort. This paper addresses the problem of localizing a speaker of interest from a novel perspective by first performing time-frequency selection before localization. The speaker of interest, namely the target speaker, is assumed to be sparsely active in the signal spectra. The target speaker-dominant time-frequency regions are separated by a speaker-aware Long Short-Term Memory (LSTM) neural network, and they are sufficient to determine the Direction of Arrival (DoA) of the target speaker. Speaker-awareness is achieved by utilizing a short target utterance to adapt the hidden layer outputs of the neural network. The instantaneous DoA estimator is based on the probabilistic complex Watson Mixture Model (cWMM), and a weighted maximum likelihood estimation of the model parameters is accordingly derived. Simulative experiments show that the proposed algorithm works well in various noisy conditions and remains robust when the signal-to-noise ratio is low and when a competing speaker exists. components, especially the direct sound components, in the observed signals [9]. These techniques include those based on the signal power [10], the coherent-to-diffuse ratio [11], and the speech presence probability [12].The motivation behind time-frequency weighting is the sparsity assumption of the signal spectra, or in other words, the assumption that only one source is active in each time frequency bin [13,14]. As suggested in [15], even if the signal is severely corrupted by noises or interferences, there exist target-dominant time-frequency regions that are sufficient enough for localization. It is also found that the human auditory system may perform source separation jointly with source localization [16]. The same motivation lies behind some fairly recent studies that perform robust source localization based on time-frequency masking [17][18][19], in which the authors propose the usage of Deep Neural Networks (DNNs) to perform mask estimation first. The masks are used to weight the narrowband estimates, and the combined algorithms achieve superior performance in adverse environments. Given that mask estimation is a well-defined task in monaural speech separation and large progress has been made with DNN [20], the combination of mask and the SRP-PHAT (or the MUSIC) algorithm is natural and straightforward. Using neural networks, there are also other practices to localize speech sources directly through spatial classification [21,22].The methods discussed above are directly applicable to TSL if the target speaker is the only speech source in the environment. When a competing speaker exits, multiple source localization techniques [23] could be applied; however, the localization results remain non-discriminative, and further post-processing for speaker identification is needed. TSL in a multi-speaker environ...

show abstract

“…This distribution has been already used in audio signal processing, although in different ways: in [11]- [13] all TF-points are used together and form a mixture of complex Watson distributions, which is utilized for speech separation [11], while in [12], [13] variational inference on the mixture parameters is employed to determine the number of mixture components which corresponds to the number of active sources. Lastly, the complex Watson distribution is used in [14] as a distance metric for wideband DOA estimation of a single source.…”

Section: Introductionmentioning

confidence: 99%

Improving narrowband DOA estimation of sound sources using the complex Watson distribution

Alexandridis

Mouchtaris

2016

2016 24th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

Narrowband direction-of-arrival (DOA) estimates for each time-frequency (TF) point offer a parametric spatial modeling of the acoustic environment which is very commonly used in many applications, such as source separation, dereverberation, and spatial audio. However, irrespective of the narrowband DOA estimation method used, many TF-points suffer from erroneous estimates due to noise and reverberation. We propose a novel technique to yield more accurate DOA estimates in the TF-domain, through statistical modeling of each TF-point with a complex Watson distribution. Then, instead of using the microphone array signals at a given TF-point to estimate the DOA, the maximum likelihood estimate of the mode vector of the distribution is used as input to the DOA estimation method. This approach results in more accurate DOA estimates and thus more accurate modeling of the acoustic environment, while it can be used with any narrowband DOA estimation method and microphone array geometry.

show abstract

DOA-estimation based on a complex Watson kernel method

Cited by 8 publications

References 17 publications

Deep Neural Network based Distance Estimation for Geometry Calibration in Acoustic Sensor Networks

Deep Neural Network based Distance Estimation for Geometry Calibration in Acoustic Sensor Networks

Target Speaker Localization Based on the Complex Watson Mixture Model and Time-Frequency Selection Neural Network

Improving narrowband DOA estimation of sound sources using the complex Watson distribution

Contact Info

Product

Resources

About