Modified Bark Spectral Distortion Research Articles

AN EFFICIENT SPEECH GENERATIVE MODEL BASED ON DETERMINISTIC/STOCHASTIC SEPARATION OF SPECTRAL ENVELOPES

The paper presents a speech generative model that provides an efficient way of generating speech waveform from its amplitude spectral envelopes. The model is based on hybrid speech representation that includes deterministic (harmonic) and stochastic (noise) components. The main idea behind the approach originates from the fact that speech signal has a determined spectral structure that is statistically bound with deterministic/stochastic energy distribution in the spectrum. The performance of the model is evaluated using an experimental low-bitrate wide-band speech coder. The quality of reconstructed speech is evaluated using objective and subjective methods. Two objective quality characteristics were calculated: Modified Bark Spectral Distortion (MBSD) and Perceptual Evaluation of Speech Quality (PESQ). Narrow-band and wide-band versions of the proposed solution were compared with MELP (Mixed Excitation Linear Prediction) speech coder and AMR (Adaptive Multi-Rate) speech coder, respectively. The speech base of two female and two male speakers were used for testing. The performed tests show that overall performance of the proposed approach is speaker-dependent and it is better for male voices. Supposedly, this difference indicates the influence of pitch highness on separation accuracy. In that way, using the proposed approach in experimental speech compression system provides decent MBSD values and comparable PESQ values with AMR speech coder at 6,6 kbit/s. Additional subjective listening testsdemonstrate that the implemented coding system retains phonetic content and speaker’s identity. It proves consistency of the proposed approach.

A Human Auditory Perception Loss Function Using Modified Bark Spectral Distortion for Speech Enhancement

Human listeners often have difficulties understanding speech in the presence of background noise in daily speech communication environments. Recently, deep neural network (DNN)-based techniques have been successfully applied to speech enhancement and achieved significant improvements over the conventional approaches. However, existing DNN-based methods usually minimize the log-power spectral-based or the masking-based mean squared error (MSE) between the enhanced output and the training target (e.g., the ideal ratio mask (IRM) of the clean speech), which is not closely related to human auditory perception. In this letter, a modified bark spectral distortion loss function, which can be considered as an auditory perception-based MSE, is proposed to replace the conventional MSE in DNN-based speech enhancement approaches to further improve the objective perceptual quality. Experimental results reveal that the proposed method can obtain improved speech enhancement performance, especially in terms of objective perceptual quality in all experimental settings when compared with the DNN-based methods using the conventional MSE criterion.

Efficient speech encryption using chaotic cat map for code-excited linear prediction based coders in packet networks

The increasing importance of multimedia applications is placing a great insist on content protection and customer privacy. Communications can be intercepted, especially over wireless links. Since encryption can effectively prevent eavesdropping, its use is widely advocated. The codec G. 729 based CS-ACELP algorithm is standardized as voice codec by ITU-T for multimedia and Voice over Internet Protocol (VoIP) applications. In this paper, we introduce a speech encryption method based chaotic cat map algorithm. Cat map extended to two-dimensional NxN matrix. It takes concepts from linear algebra and uses them to change the positions of the values of the matrix. The result after applying the Cat Map will be shuffled signals that contain the same values of the original signals. We applied our encryption scheme to the standard ITU-T G.729 standard speech coder to evaluate its performance. Simulation results show that G.729 based cat map encryption is very efficient since the encrypted speech is similar to a white noise. The perceptual evaluation of speech quality (PESQ) and enhanced modified bark spectral distortion (EMBSD) tests for speech extracted from TIMIT database confirm the efficiency of our proposed scheme.

Intraframe quantization of speech line spectrum pairs for code-excited linear prediction based coders in packet networks

This paper proposes intraframe quantization schemes of line spectrum pair parameters to improve frame erasures for the ITU-T G.723.1 coder. The standard ITU-T G.723.1 coder uses an interframe quantization of the line spectrum pair parameters, which causes error propagation to the next frames. Simulation results show that our intraframe quantization schemes coding is much more robust to frame erasures than the embedded method in ITU-T G.723.1, and a typical improvement of 0.4 dB on average spectral distortion can be obtained with 40% packet loss. Enhanced modified bark spectral distortion tests, under various packet loss conditions, confirm that our proposed method is superior to the interframe algorithm embedded in the ITU-T G.723.1 coder of over 1.6. Copyright © 2012 John Wiley & Sons, Ltd.

Psychoacoustically Constrained and Distortion Minimized Speech Enhancement

This paper considers a psychoacoustically constrained and distortion minimized speech enhancement algorithm. Noise reduction, in general, leads to speech distortion, and a balanced tradeoff between noise reduction and speech distortion must be attained. A constrained optimization problem is set to reduce noise so that speech distortion is minimized while the sum of speech distortion and residual noise is kept below the masking threshold of the clean speech. Obtaining a solution to the optimization problem may be infeasible under certain conditions, and a slack variable is introduced to allow certain deviation from the constraint conditions. To estimate the power spectral density and also the masking threshold of clean speech, a speech model that assumes coexisting deterministic and stochastic components in speech is used. Experimental results show that the considered algorithm outperforms some of the more popular algorithms in terms of improvement in segmental signal-to-noise ratio (SegSNR), spectral distance (SD), modified Bark spectral distortion (MBSD), and mean opinion score (MOS).

Perceptual improvement of Wiener filtering employing a post-filter

A major drawback of many speech enhancement methods in speech applications is the generation of an annoying residual noise with musical character. Although the Wiener filter introduces less musical noise than spectral subtraction methods, such noise, however, exists and is perceptually annoying to the listener. A potential solution to this artifact is the incorporation of a psychoacoustic model in the suppression filter design. In this paper a frequency domain optimal linear estimator with perceptual post-filtering is proposed, which incorporates the masking properties of the human hearing system to render the residual noise distortion inaudible. Proposed post-processing presents a modified way to measure the tonality coefficient and relative threshold offset for an optimal estimation of the noise masking threshold. The performance of the proposed enhancement algorithm is evaluated by the segmental SNR, Modified Bark Spectral Distortion (MBSD) and Perceptual Evaluation of Speech Quality (PESQ) measures under various noisy environments and yields better results compared to the Wiener filtering based on Ephraim-Malah's decision-directed approach.

Adaptive noise spectral estimation for spectral subtraction speech enhancement

An adaptive scheme for noise spectral estimation is proposed to cope with the power spectral subtraction method for speech enhancement. The use of such a noise spectral estimate helps eliminate residual noise without increasing speech distortion. Improvements in the segmental signal-to-noise ratio and modified bark spectral distortion measures are evidently seen with 192 TIMIT sentences corrupted by four types of broadband noise taken from the Noisex-92 database. Moreover, incorporation of this noise adaptation scheme into the constrained parameter estimator is demonstrated. Mean opinion score listening tests confirm that the proposed subtractive scheme yields better results than that acquired by subtracting an averaged noise power spectrum.

Audible Noise Reduction in Eigendomain for Speech Enhancement

A signal subspace scheme based on masking properties is proposed for enhancement of speech degraded by additive noise. Since the masking properties are related to the critical frequency band that is derived from the characteristics of human cochlea, the incorporation of masking threshold into a subspace technique requires the transformation between the frequency and eigen domains. We present and apply an invertible transformation between the frequency and eigen domains. In this paper, we use masking properties of the human auditory system to define the audible noise quantity in the eigendomain. We derive the eigen-decomposition of the estimated speech autocorrelation matrix with the assumption of white noise. Subsequently, an audible noise reduction scheme is developed based on a signal subspace technique, and the implementation of our proposed scheme is outlined. We further extend the scheme to the colored noise case. Simulation results show the superiority of our proposed scheme over other existing subspace methods in terms of segmental signal-to-noise ratio (SNR), perceptual evaluation of speech quality (PESQ), modified Bark spectral distortion (MBSD), spectrogram and informal listening tests.

Speech enhancement using constrained spectral amplitude subtraction based on noncausal a priori SNR

Two gain forms of spectral amplitude subtraction are derived theoretically without neglecting the correlation of speech and noise spectrum during the period of a frame. In the implementation, the constrained gain is expressed as a function of noncausal a priori SNR (Signal-to-Noise Ratio). Noise and noncausal a priori SNR are estimated from the multitaper spectrum of the noisy signal with algorithms modified to be suitable for the multitaper spectrum. Objective evaluations show that in case of white Gaussian noise the proposed method outperforms some methods based on LSA (Log Spectral Amplitude) in terms of MBSD (Modified Bark Spectral Distortion), segmental SNR and overall SNR, and informal listening tests show that speech reconstructed in this way has little speech distortion and musical noise is nearly inaudible even at low SNR.