Minimum Mean-square Error Log-spectral Amplitude Research Articles

Dual-stream Noise and Speech Information Perception based Speech Enhancement

In real-world scenarios, dynamic ambient noise often degrades speech quality, highlighting the need for advanced speech enhancement techniques. Traditional methods, which rely on static embeddings as auxiliary features, struggle to address the complexities of varying noise conditions. To overcome this, we propose a Dual-stream Noise and Speech Information Perception (DNSIP) approach that dynamically detects and processes both noise and speech through innovative information extraction and suppression mechanisms. Initially, non-speech segments predominantly contain environmental noise, while speech segments carry information about the intended speaker. To handle this dynamic nature, real-time voice activity detection (VAD) is employed to accurately differentiate between speech and noise components. Building on VAD estimates, we propose an innovative information extraction framework that selectively extracts relevant noise and speech features from the noisy input, establishing a dual-stream network for concurrent noise and speech learning. To account for the temporal and spectral variability of noise and speech, a frequency-sequence attention mechanism is integrated, enhancing the model’s ability to learn contextual and spectral dependencies. Additionally, an information suppression module is introduced to minimize cross-stream interference by attenuating noise within the speech stream and suppressing speech content within the noise stream. The derived noise and speech spectrograms are then utilized to formulate a minimum mean square error log-spectral amplitude (MMSE-LSA) estimator for robust speech enhancement. Experimental evaluations on the WSJ0 and VCTK+DEMAND datasets demonstrate that our DNSIP approach surpasses existing state-of-the-art methods, underscoring its efficacy in challenging acoustic environments.

Improved Non-Negative Matrix Factorization-Based Noise Reduction of Leakage Acoustic Signals.

The detection of gas leaks using acoustic signals is often compromised by environmental noise, which significantly impacts the accuracy of subsequent leak identification. Current noise reduction algorithms based on non-negative matrix factorization (NMF) typically utilize the Euclidean distance as their objective function, which can exacerbate noise anomalies. Moreover, these algorithms predominantly rely on simple techniques like Wiener filtering to estimate the amplitude spectrum of pure signals. This approach, however, falls short in accurately estimating the amplitude spectrum of non-stationary signals. Consequently, this paper proposes an improved non-negative matrix factorization (INMF) noise reduction algorithm that enhances the traditional NMF by refining both the objective function and the amplitude spectrum estimation process for reconstructed signals. The improved algorithm replaces the conventional Euclidean distance with the Kullback-Leibler (KL) divergence and incorporates noise and sparse constraint terms into the objective function to mitigate the adverse effects of signal amplification. Unlike traditional methods such as Wiener filtering, the proposed algorithm employs an adaptive Minimum Mean-Square Error-Log Spectral Amplitude (MMSE-LSA) method to estimate the amplitude spectrum of non-stationary signals adaptively across varying signal-to-noise ratios. Comparative experiments demonstrate that the INMF algorithm significantly outperforms existing methods in denoising leakage acoustic signals.

Microphone array speech enhancement based on optimized IMCRA

Microphone array speech enhancement algorithm uses temporal and spatial informa- tion to improve the performance of speech noise reduction significantly. By combining noise estimation algorithm with microphone array speech enhancement, the accuracy of noise estimation is improved, and the computation is reduced. In traditional noise es- timation algorithms, the noise power spectrum is not updated in the presence of speech, which leads to the delay and deviation of noise spectrum estimation. An optimized im- proved minimum controlled recursion average speech enhancement algorithm, based on a microphone matrix is proposed in this paper. It consists of three parts. The first part is the preprocessing, divided into two branches: the upper branch enhances the speech signal, and the lower branch gets the noise. The second part is the optimized improved minimum controlled recursive averaging. The noise power spectrum is updated not only in the non-speech segments but also in the speech segments. Fi- nally, according to the estimated noise power spectrum, the minimum mean-square error log-spectral amplitude algorithm is used to enhance speech. Testing data are from TIMIT and Noisex-92 databases. Short-time objective intelligibility and seg- mental signal-to-noise ratio are chosen as evaluation metrics. Experimental results show that the proposed speech enhancement algorithm can improve the segmental signal-to-noise ratio and short-time objective intelligibility for various noise types at different signal-to-noise ratio levels.

On pre-image iterations for speech enhancement.

In this paper, we apply kernel PCA for speech enhancement and derive pre-image iterations for speech enhancement. Both methods make use of a Gaussian kernel. The kernel variance serves as tuning parameter that has to be adapted according to the SNR and the desired degree of de-noising. We develop a method to derive a suitable value for the kernel variance from a noise estimate to adapt pre-image iterations to arbitrary SNRs. In experiments, we compare the performance of kernel PCA and pre-image iterations in terms of objective speech quality measures and automatic speech recognition. The speech data is corrupted by white and colored noise at 0, 5, 10, and 15 dB SNR. As a benchmark, we provide results of the generalized subspace method, of spectral subtraction, and of the minimum mean-square error log-spectral amplitude estimator. In terms of the scores of the PEASS (Perceptual Evaluation Methods for Audio Source Separation) toolbox, the proposed methods achieve a similar performance as the reference methods. The speech recognition experiments show that the utterances processed by pre-image iterations achieve a consistently better word recognition accuracy than the unprocessed noisy utterances and than the utterances processed by the generalized subspace method.

Speech Processing System Using a Noise Reduction Neural Network Based on FFT Spectrums

This paper proposes a speech processing system based on a model of the human auditory system and a noise reduction neural network with fast Fourier transform (FFT) amplitude and phase spectrums for noise reduction under background noise environments. The proposed system reduces noise signals by using the proposed neural network based on FFT amplitude spectrums and phase spectrums, then implements auditory processing frame by frame after detecting voiced and transitional sections for each frame. The results of the proposed system are compared with the results of a conventional spectral subtraction method and minimum mean-square error log-spectral amplitude estimator at different noise levels. The effectiveness of the proposed system is experimentally confirmed based on measuring the signal-to-noise ratio (SNR). In this experiment, the maximal improvement in the output SNR values with the proposed method is approximately 11.5 dB better for car noise, and 11.0 dB better for street noise, when compared with a conventional spectral subtraction method.

Use of speech presence uncertainty with MMSE spectral energy estimation for robust automatic speech recognition

In this paper, we investigate the use of the minimum mean square error (MMSE) spectral energy estimator for use in environment-robust automatic speech recognition (ASR). In the past, it has been common to use the MMSE log-spectral amplitude estimator for this task. However, this estimator was originally derived under subjective human listening criteria. Therefore its complex suppression rule may not be optimal for use in ASR. On the other hand, it can be shown that the MMSE spectral energy estimator is closely related to the MMSE Mel-frequency cepstral coefficient (MFCC) estimator. Despite this, the spectral energy estimator has tended to suffer from the problem of excessive residual noise. We examine the cause of this residual noise and show that the introduction of a heuristic based speech presence uncertainty (SPU) can significantly improve its performance as a front-end ASR enhancement regime. The proposed spectral energy SPU estimator is evaluated on the Aurora2, RM and OLLO2 speech recognition tasks and can be shown to significantly improve additive noise robustness over the more common spectral amplitude and log-spectral amplitude estimators.

Speech intelligibility improvement using convolutive blind source separation assisted by denoising algorithms

The present study is concerned with the blind source separation (BSS) of speech and speech-shaped noise sources. All recordings were carried out in an anechoic chamber using a dummy head (two microphones, one in each ear). The program which implements the algorithm for BSS of convolutive mixtures introduced by Parra and Spence [Parra, L., Spence, C., 2000a. Convolutive blind source separation of non-stationary sources. IEEE Trans. Speech Audio Process. 8(3), 320–327 (US Patent US6167417)] was used to separate out the signals. In the postprocessing phase two different denoising algorithms were used. The first was based on a minimum mean-square error log-spectral amplitude estimator [Ephraim, E., Malah, D., 1985. Speech enhancement using a minimum mean-square error log-spectral amplitude estimator. IEEE Trans. Speech Audio Process. ASSP-33(2), 443–445], while the second one was based on Wiener filter in which the concept of an a priori signal-to-noise estimation presented by Ephraim (as mentioned above) was applied [Scalart, P., Filho, J.V., 1996. Speech enhancement based on a priori signal to noise estimation. IEEE Internat. Conf. Acoust. Speech Signal Process. 1, 629–632]. Non-sense word tests were used as a target speech in both cases while one or two disturbing sources were used as interferences. The speech intelligibility before and after the BSS was measured for three subjects with audiologically normal hearing. Next the speech signal after BSS was denoised and presented to the same listeners. The results revealed some ambiguities caused by the insufficient number of microphones compared to the number of sound sources. For one disturbance only, the intelligibility improvement was significant. However, when there were two disturbances and the target speech, the separation was much poorer. The additional denoising, as could be expected, raises the intelligibility slightly. Although the BSS method requires more research on optimization, the results of the investigation imply that it may be applied to hearing aids in the future.

Compensating Acoustic Mismatch Using Class-Based Histogram Equalization for Robust Speech Recognition

A new class-based histogram equalization method is proposed for robust speech recognition. The proposed method aims at not only compensating for an acoustic mismatch between training and test environments but also reducing the two fundamental limitations of the conventional histogram equalization method, the discrepancy between the phonetic distributions of training and test speech data, and the nonmonotonic transformation caused by the acoustic mismatch. The algorithm employs multiple class-specific reference and test cumulative distribution functions, classifies noisy test features into their corresponding classes, and equalizes the features by using their corresponding class reference and test distributions. The minimum mean-square error log-spectral amplitude (MMSE-LSA)-based speech enhancement is added just prior to the baseline feature extraction to reduce the corruption by additive noise. The experiments on the Aurora2 database proved the effectiveness of the proposed method by reducing relative errors by over the mel-cepstral-based features and by over the conventional histogram equalization method, respectively.

Speech Enhancement with Natural Sounding Residual Noise Based on Connected Time-Frequency Speech Presence Regions

We propose time-frequency domain methods for noise estimation and speech enhancement. A speech presence detection method is used to find connected time-frequency regions of speech presence. These regions are used by a noise estimationmethod and both the speech presence decisions and the noise estimate are used in the speech enhancement method. Different attenuation rules are applied to regions with and without speech presence to achieve enhanced speech with natural sounding attenuated background noise. The proposed speech enhancement method has a computational complexity, which makes it feasible for application in hearing aids. An informal listening test shows that the proposed speech enhancement method has significantly higher mean opinion scores than minimum mean-square error log-spectral amplitude (MMSE-LSA) and decision-directed MMSE-LSA.

Incorporating a Psychoacoustical Model in Frequency Domain Speech Enhancement

A frequency domain optimal linear estimator is proposed which incorporates the masking properties of the human auditory system to make the residual noise distortion inaudible. The use of wavelet-thresholded multitaper spectra is also proposed for frequency-domain speech enhancement methods as an alternative to the traditional fast Fourier transform (FFT)-based magnitude spectra. Experiments with multitalker babble noise indicated that the proposed estimator outperformed the minimum mean-square error log-spectral amplitude estimator (MMSE-LSA), particularly when wavelet-thresholded multitaper spectra were used in place of the FFT spectra.