Application of the tuned Kalman filter in speech enhancement (original) (raw)
Related papers
Robustness and Sensitivity Tuning of the Kalman Filter for Speech Enhancement
Signals, 2021
Inaccurate estimates of the linear prediction coefficient (LPC) and noise variance introduce bias in Kalman filter (KF) gain and degrade speech enhancement performance. The existing methods propose a tuning of the biased Kalman gain, particularly in stationary noise conditions. This paper introduces a tuning of the KF gain for speech enhancement in real-life noise conditions. First, we estimate noise from each noisy speech frame using a speech presence probability (SPP) method to compute the noise variance. Then, we construct a whitening filter (with its coefficients computed from the estimated noise) to pre-whiten each noisy speech frame prior to computing the speech LPC parameters. We then construct the KF with the estimated parameters, where the robustness metric offsets the bias in KF gain during speech absence of noisy speech to that of the sensitivity metric during speech presence to achieve better noise reduction. The noise variance and the speech model parameters are adopted...
A perceptual kalman filtering-based approach for speech enhancement
Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings., 2003
A new approach for single channel speech enhancement based on Kalman filtering and masking properties of the human auditory system is proposed in the paper. A standard time-varying Kalman filtering method is extended by combining the calculation of noise masking thresholds during the process of parameter updating. Simulation results of a traditional spectral subtraction method, an extended spectral subtraction with masking properties method, a standard Kalman filtering based method, and the new proposed approach are computed and compared. The new approach has no delay and better Perceptual Evaluation of Speech Quality scores (PESQ, ITU-T P.862), with no Voice Activity Detection (VAD) required. The PESQ score improvement obtained by the proposed method is about 0.3 compared with the original noisy signal. The new approach can produce PESQ scores of 0.1 to 0.2 better than the standard Kalman filtering method.
Kalman Filtering with Machine Learning Methods for Speech Enhancement
2021
Speech corrupted by background noise (or noisy speech) can reduce the efficiency of communication between man-man and man-machine. A speech enhancement algorithm (SEA) can be used to suppress the embedded background noise and increase the quality and intelligibility of noisy speech. Many applications, such as speech communication systems, hearing aid devices, and speech recognition systems, typically rely upon speech enhancement algorithms for robustness. This dissertation focuses on single-channel speech enhancement using Kalman filtering with machine learning methods. In Kalman filter (KF)-based speech enhancement, each clean speech frame is represented by an auto-regressive (AR) process, whose parameters comprise the linear prediction coefficients (LPCs) and prediction error variance. The LPC parameters and the additive noise variance are used to form the recursive equations of the KF. In augmented KF (AKF), both the clean speech and additive noise LPC parameters are incorporated...
Sensitivity Metric-Based Tuning of the Augmented Kalman Filter for Speech Enhancement
2020 14th International Conference on Signal Processing and Communication Systems (ICSPCS), 2020
The state-of-the-art robustness metric-based tuning of the augmented Kalman filter (AKF) gives an under-estimated Kalman gain, resulting distortion in the enhanced speech during colored noise suppression. This paper introduces a sensitivity metric-based tuning of the AKF for enhancing speech corrupted with different noises. Specifically, we observe that the sensitivity metric-based tuning of the AKF overcomes the under-estimation issues of Kalman gain in the existing method. It is shown that the reduced-biased Kalman gain enables the AKF to restrict the residual noise passed to the enhanced speech. It also minimizes the distortion in the enhanced speech. Objective and subjective testing on NOIZEUS corpus reveal that the enhanced speech produced by the proposed method exhibits higher quality as well as intelligibility than the benchmark methods in colored and non-stationary noise conditions for a wide range of SNR levels.
Perceptual Kalman filtering for speech enhancement in colored noise
2004 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2004
A new method for speech enhancement in colored noise is proposed in this paper. A Kalman filter concatenated with a post-filter based on masking properties of human auditory systems is proposed for the problem. A recursive approach to compute the noise covariance matrix is used for estimating the colored noise statistics. In the post-filter, both time domain masking properties and frequency domain masking properties are taken into account. From the calculated masking level, the noisy speech spectrum is adjusted accordingly. Simulation results show that the proposed approach has the best performance compared with other recent methods, evaluated with PESQ scores.
Noise free Speech Enhancement based on Fast Adaptive Kalman Filtering Algorithm
The speech enhancement is one of the effective techniques to solve speech degraded by noise. In this paper a fast speech enhancement method for noisy speech signals is presented, which is based on improved Kalman filtering. The conventional Kalman filter algorithm for speech enhancement needs to calculate the parameters of AR (auto-regressive) model, and perform a lot of matrix operations, which usually is non-adaptive. The speech enhancement algorithm proposed in this paper eliminates the matrix operations and reduces the calculating time by only constantly updating the first value of state vector X(n). We design a coefficient factor for adaptive filtering, to automatically amend the estimation of environmental noise by the observation data. Simulation results show that the fast adaptive algorithm using Kalman filtering is effective for speech enhancement.
International Journal of Signal Processing Systems, 2019
This paper presents an iterative Kalman filter (IT-KF) with a reduced-biased Kalman gain for single channel speech enhancement in Non-stationary Noise Conditions (NNCs). The proposed IT-KF aims to offset the bias in Kalman gain through efficient parameter estimation leading to improve the speech enhancement performance. To do this, we introduce a Decision Directed (DD) and a posteriori SNR based noise variance estimation method controlled through Speech Activity Detector (SAD). The proposed SAD incorporates a majority voting of three distinct SAD fusions. The LPC parameters are computed from the pre-smoothing of noisy speech. With these initial estimated parameters, an IT-KF processes the noisy speech at first iteration. The parameters are re-estimated from the processed speech, readjust the Kalman gain, and the process is repeated at second iteration. It is shown that the adjusted Kalman gain enables the IT-KF to minimize the remaining artifacts of the processed speech, yielding the enhanced speech. Extensive simulation results reveal that the proposed method outperforms other benchmark methods in NNCs for a wide range of SNRs.
Speech enhancement based on Kalman filtering and EM algorithm
1991
In this paper, speech enhancement via Kalman filtering is considered. It is generally agreed that the quality of the estimate of speech production model parameters is crucial to the performance of the Kalman filter. The Kalman filter with a more accurate estimate of the LPC parameters will generally achieve better noise cancellation results. In practice only the noisy speech is available for the LPC analysis. Then the estimate of the LPC parameters is usually inaccurate, which in turn degrades the performance of the Kalman filter. In order to overcome the problem, we propose in this paper a Kalman filtering scheme applied in conjunction with the EM algorithm. Simulation results demonstrate the expected performance improvement in term of signal-to-ratio (SNR) gains by the new method.
Perceptually motivated pre-filter for speech enhancement using Kalman filtering
2007 6th International Conference on Information, Communications & Signal Processing, 2007
This paper proposes a novel pre-filter for Kalman filter based speech enhancement. Our aim is to reduce coloured noise, while retaining speech quality by exploiting the properties of the human auditory system. The proposed pre-filter uses temporal and simultaneous masking thresholds to shape the noisy speech spectrum in order to obtain a better estimate of the AR coefficients. These coefficients are then used to obtain a perceptual filter to weight the noise spectrum before applying the Kalman filter. The proposed noise reduction technique is compared to the Wiener filter, Perceptual Wiener filter and the standard Kalman Filter in 5 dB car noise environments. PESQ scores and subjective test results show that the proposed prefilter based enhancement outperforms other common techniques.