Real-Time Implementation of a Distributed Voice Activity Detector

Berisha, Visar; Kwon, Homin; Spanias, S.

doi:10.1109/sam.2006.1706216

Cited by 13 publications

(11 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To decide whether to use (24) or (25), the condition number of the matrix A k does not necessarily have to be known. In principle, it is always better to replace the K − 1 auxiliary channels in x k as in formula (24), where a different q should be chosen for every p. Indeed, since microphones of different nodes are typically far apart from each other, better conditioned steering matrices are then obtained.…”

Section: Robust Danse (R-danse)mentioning

confidence: 99%

“…For example, formula (24) defines the arc (w kk (p),w qq (l)). A vertex v that has no departing arc is referred to as a direct estimation filter (DEF), that is, the signal to be estimated is the desired speech component in one of the node's own microphone signals, as in formula (25). To illustrate this, a possible graph is shown in Figure 5 for DANSE 2 applied to the scenario described in Section 3, where the hearing aid users are now listening to two speakers, that is, speakers B and C. Since the microphone signals of node 1 have a low SNR, the two desired signals in x 1 that are used in the computation of W 11 are replaced by the filtered desired speech component in the received signals from higher SNR nodes 2 and 4, that is, w 22 (1) H x 2 and w 44 (1) H x 4 , respectively.…”

Section: Convergence Of R-dansementioning

confidence: 99%

See 1 more Smart Citation

Robust Distributed Noise Reduction in Hearing Aids with External Acoustic Sensor Nodes

Bertrand

Moonen

2009

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

The benefit of using external acoustic sensor nodes for noise reduction in hearing aids is demonstrated in a simulated acoustic scenario with multiple sound sources. A distributed adaptive node-specific signal estimation (DANSE) algorithm, that has a reduced communication bandwidth and computational load, is evaluated. Batch-mode simulations compare the noise reduction performance of a centralized multi-channel Wiener filter (MWF) with DANSE. In the simulated scenario, DANSE is observed not to be able to achieve the same performance as its centralized MWF equivalent, although in theory both should generate the same set of filters. A modification to DANSE is proposed to increase its robustness, yielding smaller discrepancy between the performance of DANSE and the centralized MWF. Furthermore, the influence of several parameters such as the DFT size used for frequency domain processing and possible delays in the communication link between nodes is investigated.

show abstract

Section: Robust Danse (R-danse)mentioning

confidence: 99%

Section: Convergence Of R-dansementioning

confidence: 99%

Robust Distributed Noise Reduction in Hearing Aids with External Acoustic Sensor Nodes

Bertrand

Moonen

2009

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

show abstract

“…Each device could in theory run its own noise attenuation, source separation, voice activity detection, keyword spotting and speech recognition algorithms and more, but those algorithms would then be redundant, since multiple devices run the same tasks. For improved efficiency and accuracy, we can instead use, for example, a distributed voice activity detector among local devices [26], distributed beamforming [16] or distributed speech recognition [27].…”

Section: Local Collaborationmentioning

confidence: 99%

Speech Coding, Speech Interfaces and IOT - Opportunities and Challenges

Bäckström

2018

2018 52nd Asilomar Conference on Signals, Systems, and Computers

View full text Add to dashboard Cite

Recent speech and audio coding standards such as 3GPP Enhanced Voice Services match the foreseeable needs and requirements in transmission of speech and audio, when using current transmission infrastructure and applications. Trends in Internet-of-Things technology and development in personal digital assistants (PDAs) however begs us to consider future requirements for speech and audio codecs. The opportunities and challenges are here summarized in three concepts: collaboration, unification and privacy. First, an increasing number of devices will in the future be speechoperated, whereby the ability to focus voice commands to a specific devices becomes essential. We therefore need methods which allows collaboration between devices, such that ambiguities can be resolved. Second, such collaboration can be achieved with a unified and standardized communication protocol between voice-operated devices. To achieve such collaboration protocols, we need to develop distributed speech coding technology for ad-hoc IoT networks. Finally however, collaboration will increase the demand for privacy protection in speech interfaces and it is therefore likely that technologies for supporting privacy and generating trust will be in high demand.

show abstract

“…We have found a clear relation between the log-likelihood for a certainÛ and the localization error. Thus, we propose using expression (8) as the fitness function. Figure 4 shows the relation between the log-likelihood and the pairwise node distance error for all possible values ofÛ in a network with = 4.…”

Section: Uncertainty Solutionmentioning

confidence: 99%

“…The relative location of the nodes provides us with sufficient spatial information to implement a wireless microphone array (WMA). WMAs have many potential applications in distributed audio processing, such as speech enhancement [4], blind source separation and echo cancelation [5], speaker localization and tracking [6,7], and voice activity detection [8].…”

Section: Introductionmentioning

confidence: 99%

Indoor Self-Localization and Orientation Estimation of Smartphones Using Acoustic Signals

Sánchez-Hevia

Ayllón

Gil-Pita

et al. 2017

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

We propose a new acoustic self-localization and orientation estimation algorithm for smartphones networks composed of commercial off-the-shelf devices equipped with two microphones and a speaker. Each smartphone acts as an acoustic transceiver, which emits and receives acoustic signals. Node locations are found by combining estimates of the range and direction of arrival (DoA) between node pairs using a maximum likelihood (ML) estimator. A tailored optimization algorithm is proposed to simultaneously solve the DoA uncertainty problem that arises from the use of only 2 microphones per node and obtain the azimuthal orientation of each node without requiring an electronic compass.

show abstract

Real-Time Implementation of a Distributed Voice Activity Detector

Cited by 13 publications

References 5 publications

Robust Distributed Noise Reduction in Hearing Aids with External Acoustic Sensor Nodes

Robust Distributed Noise Reduction in Hearing Aids with External Acoustic Sensor Nodes

Speech Coding, Speech Interfaces and IOT - Opportunities and Challenges

Indoor Self-Localization and Orientation Estimation of Smartphones Using Acoustic Signals

Contact Info

Product

Resources

About