A Comparative Analysis of Speech Enhancement Techniques Based on Sparsity Features

The spectral subtraction method is a conventional approach for single channel speech enhancement. The basic principle of this method is to estimate the short-time spectral magnitude of speech by subtracting estimated noise from the noisy speech spectrum and to combines it with the phase of the noisy speech. Besides reducing the noise, this method generates an unnatural and unpleasant noise, called remnant noise. This paper proposes a novel algorithm to reduce the remnant noise, and thus improving the overall quality of the enhanced speech. In this algorithm, the output of multi-band spectral subtraction (MBSS) method is used as the input signal again for next iteration process. After the MBSS method, the additive noise is changed to remnant noise. The remnant noise is re-estimated at each iteration. The new estimated noise, furthermore, is been used to process the next MBSS. This procedure is iterated a small number of times. The simulation results as well as informal subjective evaluations prove that the speech enhanced by proposed algorithm is more pleasant to listeners than the conventional MBSS algorithm. This reveals that the proposed algorithm reduces remnant noise satisfactorily and produces good speech quality with improved signal-to-noise ratio.

An Iterative Graph Spectral Subtraction Method for Speech Enhancement

A new voice activity detection (VAD) algorithm with soft decision output in Mel-frequency domain is developed based on hidden Markov model (HMM) and is incorporated in an HMM-based speech enhancement system. The proposed VAD uses a two-state ergodic HMM representing speech presence and speech absence. The states are constructed from noisy speech and noise HMMs used in the speech enhancement system. This composite model provides a robust detection of speech segments in the presence of noise and obviates the need for extra modeling in HMM-based speech enhancement applications. As the main purpose of the proposed VAD is to detect speech segments accurately, a hang-over mechanism is proposed and is applied on the output of the VAD to improve the speech detection rate. The VAD is integrated in the HMM-based speech enhancement system in Mel-frequency spectral (MFS) and cepstral (MFC) domains. The performance of the proposed VAD, the effectiveness of the hang-over mechanism and the performance of the VAD-integrated speech enhancement system are evaluated on four noise types at different SNR levels. The experimental results confirm the superiority of the proposed VAD compared to the reference methods particularly for speech detection rate at the dominant noisy conditions.

Sensorineural hearing impairment is associated with increased intraspeech spectral masking and results in degraded speech perception in noisy environment due to increased masking. Speech enhancement using spectral subtraction can be used for suppressing the external noise. Multiband frequency compression of the complex spectral samples has been reported to reduce the effects of increased intraspeech masking. A combination of these techniques is implemented for real-time processing for improving speech perception by persons with moderate sensorineural loss. For reducing computational complexity and memory requirement, spectral subtraction is carried out using a cascaded-median based estimation of the noise spectrum without voice activity detection. Multi-band frequency compression, based on auditory critical bandwidths, is carried out using fixed-frame processing along with least-squares error based signal estimation to reduce the processing delay. To reduce computational complexity the two processing stages share the FFT based analysis-synthesis. The processing is implemented and tested for satisfactory operation, with sampling frequency of 10 kHz, 25.6 ms window with 75% overlap, using a 16-bit fixed-point DSP processor. The real-time operation is achieved with signal delay of approximately 36 ms and using about one-third of the computing capacity of the processor.

In this paper, we present a new Speech Enhancement (SE) technique capable of running on a smartphone, as an assistive device for hearing aids (HAs). The developed method incorporates the coherence between the speech and noise signals to obtain a SE gain function which is used in conjunction with the gain function obtained by Spectral Subtraction using adaptive gain averaging. SE using coherence based gain function is found to suppress the background noise well, while inducing speech distortion. On the other hand, SE using Spectral Subtraction improves speech quality with tolerable speech distortion, but introduces background musical noise for certain noise types. The weighted fusion of the two gain functions strikes a balance between noise suppression and speech distortion. Also it allows the user to control the weighting factor based on the noisy environment and their comfort level of hearing. The developed method is computationally fast and operates in real-time. The proposed method was evaluated for machinery, babble, and car noise types, using both objective and subjective measures for both quality and intelligibility of the enhanced speech. The results show significant improvements in comparison with stand-alone Spectral Subtraction with weighted gain averaging SE methods.

Time-Frequency (T-F) domain masking is currently the dominant method for single-channel speech enhancement, while little attention has been paid to phase information. A speech enhancement method, named PHASEN-SS, is proposed in this paper. Our method is divided into two steps, first a deep neural network (DNN) with two-branch communication using a combination of mask and phase for speech enhancement, and then a data post-processing after the DNN processes the noisy speech. PHASEN-SS uses two branches to predict the amplitude mask and the phase separately, which improves the accuracy of prediction by exchanging information between two branches, and then further the enhancement by denoising the residual noise through spectral subtraction. The experiments are conducted on the publicly available Voice Bank + DEMAND dataset, as well as a noisy speech dataset is synthesized with 4 common noises in Noise92 and Voice Bank clean speech according to the specified signal-to-noise ratio (SNR). The results show that the proposed method improves on the original one, and has better robustness to speech containing babble noise at higher SNRs for different SNRs.

The basic problem suffered by a communication system is in the removal of additive background noise.Spectral Subtraction method (SSM) has been successfully implemented to suppress the background noise.This paper proposed a novel hybrid system for enhancing noise-corrupted speech which involves a parallel combination of Spectral Subtraction and soft thresholding method in wavelet domain for speech enhancement.The performance of hybrid system is compared with both Spectral Subtraction method and Wavelet thresholding technique (WTT) and found to have better SNR improvement.Implementation and evaluation have been made using MATLAB.

Real and imaginary modulation spectral subtraction for speech enhancement

A spectral subtraction technique is presented for real-time speech enhancement in the aids used by hearing impaired listeners. For reducing computational complexity and memory requirement, it uses a cascaded-median based estimation of the noise spectrum without voice activity detection. The technique is implemented and tested for satisfactory real-time operation, with sampling frequency of 12 kHz, processing using window length of 30 ms with 50% overlap, and noise estimation by 3-frame 4-stage cascaded-median, on a 16-bit fixed-point DSP processor with on-chip FFT hardware. Enhancement of speech with different types of additive stationary and non-stationary noise resulted in SNR advantage of 4 – 13 dB.

This study proposes a bi-directional recurrent neural network (Bi-RNN) post-processing method for speech enhancement (SE) at low signal-to noise ratios (SNR). Current speech enhancement solutions performed badly under low SNR situations. Loizou and Kim proposed a solution to reduce speech distortion errors in time-frequency (T-F) domain but it requires the knowledge of ground truth. As ground truth is unknown in real-life applications, the current study proposes to use a Bi-RNN to implement Loizou and Kim’s solution as a post-processing method for SE engines. Our solutions do not require prior knowledge of ground truth. The effectiveness of the proposed method is investigated with a spectral subtraction (SS) SE engine, a non-negative matrix factorization (NMF) SE engine, and a deep neural network ideal ratio mask (DNN-IRM) SE engine, under matched/mis-matched noise and different SNR conditions. Experimental results demonstrate that the proposed post-processing method effectively improved both perceptual evaluation of speech quality (PESQ) and short-time objective intelligibility (STOI) for all of these SE engines, especially at low SNR conditions.

Voice activity detection (VAD) is an outstanding problem for speech transmission, enhancement and recognition. The variety and the varying nature of speech and background noise make it especially challenging. In the past years, many features emphasizing the differences between speech and noise have been proposed for their robustness. However an important problem in many areas of speech processing is the determination of presence of speech periods in a given signal. This task can be identified as a statistical hypothesis problem and its purpose is the determination to which category or class a given signal belongs. Also the classification task is often not as trivial as it appears since the increasing level of background noise leading to numerous detection errors. The selection of an adequate feature vector for signal detection and a robust decision rule is a challenging problem that affects the performance of VADs. Most algorithms are effective in numerous applications but often cause detection errors mainly due to the loss of discriminating power of the decision rule at lower SNRs. In this paper, it has been tried to extract the characteristics of noise by the VAD algorithm which can be used to smooth out the signal in silence part from the noisy environment. For further noise reduction signal then filtered in the wavelet domain using thresholding.

In order to develop a novel voice sensor to detect human voices, the use of features which are more robust to noise is an important issue. Voice sensor is also called voice activity detection (VAD). Due to that the inherent nature of the formant structure only occurred on the speech spectrogram (well-known as voiceprint), Wu et al. were the first to use band-spectral entropy (BSE) to describe the characteristics of voiceprints. However, the performance of VAD based on BSE feature was degraded in colored noise (or voiceprint-like noise) environments. In order to solve this problem, we propose the two-dimensional part-band energy entropy (TD-PBEE) parameter based on two variables: part-band partition number upon frequency index and long-term window size upon time index to further improve the BSE-based VAD algorithm. The two variables can efficiently represent the characteristics of voiceprints on each critical frequency band and use long-term information for noisy speech spectrograms, respectively. The TD-PBEE parameter can be regarded as a PBEE parameter over time. First, the strength of voiceprints can be partly enhanced by using four entropies applied to four part-bands. We can use the four part-band energy entropies for describing the voiceprints in detail. Due to the characteristics of non-stationary for speech and various noises, we will then use long-term information processing to refine the PBEE, so the voice-like noise can be distinguished from noisy speech through the concept of PBEE with long-term information. Our experiments show that the proposed feature extraction with the TD-PBEE parameter is quite insensitive to background noise. The proposed TD-PBEE-based VAD algorithm is evaluated for four types of noises and five signal-to-noise ratio (SNR) levels. We find that the accuracy of the proposed TD-PBEE-based VAD algorithm averaged over all noises and all SNR levels is better than that of other considered VAD algorithms.

Speech enhancement with Geometric Advent of Spectral subtraction using connected time-frequency regions noise estimation aims to de-noise or reduce background noise from the noisy speech for better quality, pleasantness and improved intelligibility. Numerous enhancement methods are proposed including spectral subtraction, subspace, statistical with different noise estimations. The traditional spectral subtraction techniques are reasonably simple to implement and suffer from musical noise. This study addresses the new approach for speech enhancement which has minimized the insufficiencies in traditional spectral subtraction algorithms using MCRA. This approach with noise estimation has been evolved with PESQ, the ITU-T standard; Frequency weighted segmental SNR and weighted spectral slope. The analysis shows that Geometric approach with time-frequency connected regions has improved results than old-fashioned spectral subtraction algorithms. The normal hearing tests has suggested that new approach has lower audible musical noise.

Estimation of speech absence uncertainty based on multiple linear regression analysis for speech enhancement

In this paper, a novel approach to apply GM(1,1) model in voice activity detection (VAD) is presented. The approach is termed as grey VAD (GVAD). In GVAD, GM(1,1) model is used to estimate noise in noisy speech and therefore signal where the additive signal model is assumed. By estimated noise and signal, the signal-to-noise ratio (SNR) is calculated. Based on an adaptive threshold, speech and non-speech segments are determined. The proposed GVAD is performed in the time-domain and thus has low computational complexity. In the simulation, GVAD is verified by cases with non-stationary additive white Gaussian noise and is compared with VAD in G 729 and GSM AMR. The results indicate that the proposed GVAD is able to detect voice activity appropriately. In the given examples, the performance of GVAD is better than VAD in G 729 and GSM AMR.