MMSE based noise PSD tracking with low complexity

Hendriks, Richard C.; Heusdens, Richard; Jensen, Jesper

doi:10.1109/icassp.2010.5495680

Cited by 213 publications

(199 citation statements)

References 9 publications

Supporting

Mentioning

196

Contrasting

Unclassified

Order By: Relevance

“…From (24), it then follows that , and thus, the smallest second largest eigenvalue is and the corresponding second largest eigenvalue of is . An example of a -matrix with such an eigenvalue distribution is the matrix given by (25) This is intuitively satisfying, as this probability matrix is the -matrix corresponding to a fully connected network where the probability that a node communicates with any other neighboring node is uniformly distributed.…”

Section: ) Best Connected Networkmentioning

confidence: 99%

“…For an overview on sensor network self-localization and source localization algorithms see [20] and [21], respectively. To estimate the noise PSD , we make use of the noise PSD estimator presented in [25]. Based on the two initial values and , the optimal centralized beamformer from (7) can be obtained as (11) Equation (11) shows that the distributed beamformer can be written as a ratio of two averages, and thus, it can be seen as an averaging consensus problem.…”

Section: Distributed Delay and Sum Beamformermentioning

confidence: 99%

See 1 more Smart Citation

Distributed delay and sum beamformer for speech enhancement in wireless sensor networks via randomized gossip

Zeng

Hendriks

2012

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Abstract-In this paper, we investigate the use of randomized gossip for distributed speech enhancement and present a distributed delay and sum beamformer (DDSB). In a randomly connected wireless acoustic sensor network, the DDSB estimates the desired signal at each node by communicating only with its neighbors. We first provide the asynchronous DDSB (ADDSB) where each pair of neighboring nodes updates its data asynchronously. Then, we introduce an improved general distributed synchronous averaging (IGDSA) algorithm, which can be used in any connected network, and combine that with the DDSB algorithm where multiple node pairs can update their estimates simultaneously. For convergence analysis, we first provide bounds for the worst case averaging time of the ADDSB for the best and worst connected networks, and then we compare the convergence rate of the ADDSB with the original synchronous DDSB (OSDDSB) and the improved synchronous DDSB (ISDDSB) in regular networks. This convergence rate comparison is extended to randomly connected non-regular networks using simulations. The simulation results show that the DDSB using the different updating schemes converges to the optimal estimates of the centralized beamformer and that the proposed IGDSA algorithm converges much faster than the original synchronous communication scheme, in particular for non-regular networks. Moreover, comparisons are performed with several existing distributed speech enhancement methods from literature, assuming that the steering vector is given. In the simulated scenario, the proposed method leads to a slight performance improvement at the expense of a higher communication cost. The presented method is not constrained to a certain network topology (e.g., tree connected or fully connected), while this is the case for many of the reference methods.Index Terms-Distributed delay and sum beamformer, randomized gossip, speech enhancement, wireless acoustic sensor networks.

show abstract

Section: ) Best Connected Networkmentioning

confidence: 99%

Section: Distributed Delay and Sum Beamformermentioning

confidence: 99%

Distributed delay and sum beamformer for speech enhancement in wireless sensor networks via randomized gossip

Zeng

Hendriks

2012

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The bottom-up mask is estimated using a recently proposed system described in [31], which combines masks estimated by CASA based [19] and speech enhancement based methods [32]. The speech enhancement based mask uses an LC of -5 dB.…”

Section: Methodsmentioning

confidence: 99%

Coupling binary masking and robust ASR

Narayanan

Wang

2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

We present a novel framework for performing speech separation and robust automatic speech recognition (ASR) in a unified fashion. Separation is performed by estimating the ideal binary mask (IBM), which identifies speech dominant and noise dominant units in a time-frequency (T-F) representation of the noisy signal. ASR is performed on extracted cepstral features after binary masking. Previous systems perform these steps in a sequential fashion -separation followed by recognition. The proposed framework, which we call bidirectional speech decoding (BSD), unifies these two stages. It does this by using multiple IBM estimators each of which is designed specifically for a back-end acoustic phonetic unit (BPU) of the recognizer. The standard ASR decoder is modified to use these IBM estimators to obtain BPU-specific cepstra during likelihood calculation. On the Aurora-4 robust ASR task, the proposed framework obtains a relative improvement of 17% in word error rate over the noisy baseline. It also obtains significant improvements in the quality of the estimated IBM.

show abstract

“…where k and l, denote the frequency bin index and the frame index respectively; [11] is robust at estimating PSD of the background noise signals. Two channel Wiener filtering based on a-priori SNR estimation is implemented [12] for its capability of reducing "musical noise" [3].…”

Section: Y K L and ( )mentioning

confidence: 99%

“…In our situation, this information is unknown, therefore we chose to use a single channel noise power estimator and apply it to the left and the right channels individually. In a second step, a noise PSD estimation algorithm based on the minimum mean square error (MMSE) by Hendriks et al [11] was used to estimate the noise PSD of noisy speech in each channel individually. This specific noise estimator has been shown to estimate noise power robustly, and it can track non-stationary noises with reasonably low mean estimation error and low estimation error variance [2].…”

Section: Noise Power Estimationmentioning

confidence: 99%

Speech Enhancement via Combination of Wiener Filter and Blind Source Separation

Taghia

Sang

et al. 2011

Advances in Intelligent and Soft Computing

View full text Add to dashboard Cite

Abstract. Automatic speech recognition (ASR) often fails in acoustically noisy environments. Aimed to improve speech recognition scores of an ASR in a real-life like acoustical environment, a speech pre-processing system is proposed in this paper, which consists of several stages: First, a convolutive blind source separation (BSS) is applied to the spectrogram of the signals that are pre-processed by binaural Wiener filtering (BWF). Secondly, the target speech is detected by an ASR system recognition rate based on a Hidden Markov Model (HMM). To evaluate the performance of the proposed algorithm, the signal-to-interference ratio (SIR), the improvement signal-to-noise ratio (ISNR) and the speech recognition rates of the output signals were calculated using the signal corpus of the CHiME database. The results show an improvement in SIR and ISNR, but no obvious improvement of speech recognition scores. Improvements for future research are suggested.

show abstract

MMSE based noise PSD tracking with low complexity

Cited by 213 publications

References 9 publications

Distributed delay and sum beamformer for speech enhancement in wireless sensor networks via randomized gossip

Distributed delay and sum beamformer for speech enhancement in wireless sensor networks via randomized gossip

Coupling binary masking and robust ASR

Speech Enhancement via Combination of Wiener Filter and Blind Source Separation

Contact Info

Product

Resources

About