Binaural speech enhancement with spatial cue preservation utilising simultaneous masking

Koutrouvelis, Andreas I.; Jensen, Jesper; Guo, Meng; Hendriks, Richard C.; Heusdens, Richard

doi:10.23919/eusipco.2017.8081277

Cited by 7 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Next, to measure the reduction of the interferers and diffuse noise components with the beamforming process, a signal to noise ratio gain (SNR-gain, array gain), a signal to interferers ratio gain (SIR-gain), and a signal to diffuse noise ratio gain (SDNR-gain) are computed on each side, providing the difference in dB between the SNR, SIR, and SDNR at the beamformer output and at the input reference microphone: (40) where in the above cross-and auto-PSDs x ref , v ref and n ref refer to the target, interferers and diffuse noise components at a reference microphone, while z x , z v and z n refer to the corresponding components in the beamformer output signal. Finally, to measure the target distortion on each side after processing, two measurements are used: a target Speech Distortion Ratio (SDR) and a Speech Distortion Magnitude-only distance (SDmag).…”

Section: Performance Measurementmentioning

confidence: 99%

“…A challenge for this classification algorithm is its applicability in low input SNR environments, as most T-F bins can be classified as noise-dominant, resulting in low SNR improvement and an attenuated target output, as illustrated in [39]. As an attempt to enhance the performance of this method, the classification mechanism was later modified to use the output SNR instead of the input SNR [40]. However, this method requires an estimation of the second order statistics of the noise and the target components, which, as previously described, can be challenging in some real-life time-varying multi-talker environments.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Robust Target Linearly Constrained Minimum Variance Beamformer With Spatial Cues Preservation for Binaural Hearing Aids

As'ad

Bouchard

Kamkar-Parsi

2019

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

In this paper, a binaural beamforming algorithm for hearing aid applications is introduced. The beamforming algorithm is designed to be robust to some error in the estimate of the target speaker direction. The algorithm has two main components: a robust target linearly constrained minimum variance (TLCMV) algorithm based on imposing two constraints around the estimated direction of the target signal, and a post-processor to help with the preservation of binaural cues. The robust TLCMV provides a good level of noise reduction and low level of target distortion under realistic conditions. The post-processor enhances the beamformer abilities to preserve the binaural cues for both diffuse-like background noise and directional interferers (competing speakers), while keeping a good level of noise reduction. The introduced algorithm does not require knowledge or estimation of the directional interferers' directions nor the second-order statistics of noise-only components. The introduced algorithm requires an estimate of the target speaker direction, but it is designed to be robust to some deviation from the estimated direction. Compared with recently proposed state-of-the-art methods, comprehensive evaluations are performed under complex realistic acoustic scenarios generated in both anechoic and mildly reverberant environments, considering a mismatch between estimated and true sources direction of arrival. Mismatch between the anechoic propagation models used for the design of the beamformers and the mildly reverberant propagation models used to generate the simulated directional signals is also considered. The results illustrate the robustness of the proposed algorithm to such mismatches. Index Terms-Robust LCMV, propagation model mismatch, steering vector mismatch, binaural cues preservations, noise reduction, binaural hearing aids.Hala As'ad received the M.A.Sc. degree in electrical engineering with a specialization in audio and speech processing in 2015 from the University of Ottawa, Ottawa, ON, Canada, where she is currently working toward the Ph.D. degree in electrical and computer engineering. Her doctoral research focuses on robust binaural beamforming, binaural cues preservation, and source direction of arrival detection in hearing aids. Her research interests include applied signal processing and machine learning with an emphasis on audio and speech processing, array signal processing, beamforming, speech enhancement, acoustic source localization, and hearing aids. She is the recipient of the Natural Sciences and Engineering Research Council Scholarship, the University of Ottawa Excellence Scholarship, and the Ontario Graduate Scholarship.

show abstract

Section: Performance Measurementmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Robust Target Linearly Constrained Minimum Variance Beamformer With Spatial Cues Preservation for Binaural Hearing Aids

As'ad

Bouchard

Kamkar-Parsi

2019

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…In [13], a Maximum Likelihood (ML) scheme was proposed for estimating the speech and noise PSDs. This method has been successfully used for scientific [15] as well as industrial [14,16] applications. However, typically there are some frequency bins where the ML estimation scheme suggests negative values for the speech spectrum.…”

Section: Introductionmentioning

confidence: 99%

A Constrained Maximum Likelihood Estimator of Speech and Noise Spectra with Application to Multi-Microphone Noise Reduction

Zahedi

Pedersen

Østergaard

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

One of the challenges with the implementation of multi-microphone noise reduction systems in practical applications lies in the need for the knowledge of the speech and noise covariance matrices. Recently, a method based on Maximum Likelihood (ML) estimation addressed this problem. Despite its relative success in practical setups, this method may suggest negative spectral components for the clean speech due to noise influences. In this paper, we suggest a new estimation technique that tackles this issue by enforcing a power constraint on the estimation problem. We compare the proposed method with the ML method both in synthetic and real-life scenarios using objective measures. The results suggest that the proposed method can improve speech quality without a loss of intelligibility.

show abstract

“…More precisely, after applying the BMVDR beamformer both output components exhibit the binaural cues of the desired source component, i.e., both components are perceived as coming from the direction of the desired source such that the binaural hearing advantage cannot be exploited by the auditory system. Aiming at additionally preserving the binaural cues of the noise component and hence preserving the spatial impression of the complete acoustic scene, several extensions of the binaural MWF and the BMVDR beamformer have been proposed, e.g., by incorporating constraints into the spatial filter design [10]- [15] or by mixing with scaled (noisy) reference microphone signals [9], [16]- [20].…”

mentioning

confidence: 99%

Performance Analysis of the Extended Binaural MVDR Beamformer With Partial Noise Estimation

Gosling

Marquardt

Doclo

2021

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Besides reducing undesired noise sources and limiting speech distortion, another important objective of a binaural noise reduction algorithm is the preservation of the binaural cues of all sound sources in the acoustic scene. In this paper, we consider the binaural minimum variance distortionless response beamformer with partial noise estimation (BMVDR-N), which allows to trade off between noise reduction performance and binaural cue preservation of the noise component by mixing the output signals of the BMVDR beamformer with the noisy reference microphone signals.For a directional noise source, it has been shown that incorporating an external microphone in addition to the head-mounted microphones enables both the noise reduction performance as well as the interaural time and level difference cues of the noise component to be improved in the output signals. In this paper, we consider an arbitrary noise field and analytically show that incorporating an external microphone in the BMVDR-N beamformer enables 1) a larger output signal-to-noise ratio (SNR) for the same mixing parameter, 2) the same output SNR for a larger mixing parameter, and 3) the same desired output magnitude squared coherence (MSC) of the noise component for a smaller mixing parameter to be obtained. The derived analytical expressions are firstly validated using simulated anechoic acoustic transfer functions, where the listener's head is modelled as a rigid sphere. Experimental results using recorded signals for a binaural hearing device setup in a reverberant environment also show that in a realistic scenario incorporating an external microphone in the BMVDR-N beamformer significantly improves the output SNR and reduces the mixing parameter that is required to obtain a desired output MSC of the noise component compared to using only the head-mounted microphones.

show abstract

Binaural speech enhancement with spatial cue preservation utilising simultaneous masking

Cited by 7 publications

References 14 publications

A Robust Target Linearly Constrained Minimum Variance Beamformer With Spatial Cues Preservation for Binaural Hearing Aids

A Robust Target Linearly Constrained Minimum Variance Beamformer With Spatial Cues Preservation for Binaural Hearing Aids

A Constrained Maximum Likelihood Estimator of Speech and Noise Spectra with Application to Multi-Microphone Noise Reduction

Performance Analysis of the Extended Binaural MVDR Beamformer With Partial Noise Estimation

Contact Info

Product

Resources

About