Double-talk detection in acoustic echo cancellers using zero-crossings rate

Ikram, Muhammad Z.

doi:10.1109/icassp.2015.7178144

Cited by 9 publications

(11 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…. This result can be compared with (10) obtained for the one-sample case. The generalization to more than two samples is straightforward.…”

Section: A Signal and Channel Modelsmentioning

confidence: 91%

“…The different decision regions corresponding to (10) are illustrated in the (z 2 0 (n), z 2 1 (n)) plane in Fig. 2.…”

Section: A Signal and Channel Modelsmentioning

confidence: 99%

“…Several works have proposed methods for DT detection in ECs without considerations regarding CC, such as [1], [8]- [10]. However, DT detection strategies that assume a static channel response may yield unpredictable performances in the presence of CC [11].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A New Decision-Theory-Based Framework for Echo Canceler Control

Imbiriba

Bermudez

Tourneret

et al. 2018

IEEE Trans. Signal Process.

View full text Add to dashboard Cite

A control logic has a central role in many echo cancellation systems for optimizing the performance of adaptive filters while estimating the echo path. For reliable control, accurate double-talk (DT) and channel change (CC) detectors are usually incorporated to the echo canceler. This work expands the usual detection strategy to define a classification problem characterizing four possible states of the echo canceler operation. The new formulation allow the use of decision theory to continuously control the transitions among the different modes of operation. The classification rule reduces to a low cost statistics for which it is possible to determine the probability of error under all hypotheses, allowing the classification performance to be accessed analytically. Monte Carlo simulations using synthetic and real data illustrate the reliability of the proposed method.

show abstract

“…. This result can be compared with (10) obtained for the one-sample case. The generalization to more than two samples is straightforward.…”

Section: A Signal and Channel Modelsmentioning

confidence: 91%

“…The different decision regions corresponding to (10) are illustrated in the (z 2 0 (n), z 2 1 (n)) plane in Fig. 2.…”

Section: A Signal and Channel Modelsmentioning

confidence: 99%

See 1 more Smart Citation

A New Decision-Theory-Based Framework for Echo Canceler Control

Imbiriba

Bermudez

Tourneret

et al. 2018

IEEE Trans. Signal Process.

View full text Add to dashboard Cite

show abstract

“…Without a double-talk detector that works correctly in case of double-talk, the echo canceller cannot reliably cancel echoes and distort speech sent to the far end. To detect the double-talk state, we used cross-correlation energy of the far-end and microphone signals [9] or the variance of the maximum value of the tap in the adaptive filter [10] or zero-crossing rate of error [11]. However, because the detection takes a long time, the coefficients of the filter may diverge.…”

Section: Introductionmentioning

confidence: 99%

Double-talk robust acoustic echo canceller based on CNN filter

Lee

2020

IJEEI

View full text Add to dashboard Cite

Conventional acoustic echo cancellation works by using an adaptive algorithm to identify the impulse response of the echo path. In this paper, we use the CNN(convolutional neural network) filter to remove the echo signal from the microphone input signal, so that only the speech signal is transmitted to the far-end. Using the neural network filter, weights are well converged by the general speech signal. Especially, it shows the ability to perform stable operation without divergence even in the double-talk state, in which both parties speak simultaneously. As a result of simulation, this system showed better performance and stable operation compared to the echo canceler of the adaptive filter structure. And, in double-talk, we showed the ERLE in the CNN is about 3 [dB] better than in the general neural network.

show abstract

“…Recently in [18], the authors have approached a method based on the measurement of the ZCR. A comparison has been done for DT detection.…”

Section: Introductionmentioning

confidence: 99%

Slope at Zero Crossings (ZC) of Speech Signal for Multi-Speaker Activity Detection

Ramaiah¹,

Rao²

2016

IJCI

View full text Add to dashboard Cite

Multi-Speaker activity (MSA) detection helps in detecting the presence of whether the speech signals has a single speaker or multiple speaker speeches in the speech signal. It is easy to calculate the slope at ZCs (zero crossings) of the speech signal and makes a comparison with a suitable threshold (Th). Multi-speaker is declared as and when the zero crossing value exceeds the threshold. The impact of the proposed technique is compared to the existing technique by calculating the sample-by-sample ZCR (Zero crossing rate) value is demonstrated. Experimental results prove that the proposed ZCR technique achieves accurate results than the traditional techniques for MSA detection that uses the cepstrum resynthesis residual magnitude (CRRM) in the literature.

show abstract

Double-talk detection in acoustic echo cancellers using zero-crossings rate

Cited by 9 publications

References 9 publications

A New Decision-Theory-Based Framework for Echo Canceler Control

A New Decision-Theory-Based Framework for Echo Canceler Control

Double-talk robust acoustic echo canceller based on CNN filter

Slope at Zero Crossings (ZC) of Speech Signal for Multi-Speaker Activity Detection

Contact Info

Product

Resources

About