Speech enhancement using sparse dictionary learning in wavelet packet transform domain. (July 2017)

• Record Type: Journal Article
• Authors: Mavaddaty, Samira; Ahadi, Seyed Mohammad; Seyedin, Sanaz
• Is Part Of: Computer speech & language. Volume 44(2017)
• Page Start: 22
• Page End: 47
• Publication Date: 2017-07
• Subjects: Speech enhancement -- Dictionary learning -- Sparse representation -- Domain adaptation -- Voice activity detector -- Wavelet packet transform; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2017.01.009
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: A new learning-based speech enhancement method via sparse representation in wavelet packet transform domain is presented. The dictionary learning procedure for training data of speech and noise signals based on coherence criterion are proposed. The supervised and semi-supervised enhancement algorithms are introduced using the presented voice activity detector. The proposed VAD is employed based on the energy of sparse coefficient matrices in each speech enhancement scenario. Domain adaptation method that alleviates the mismatch between train and test steps is employed in enhancement procedure. Abstract: Sparse coding, as a successful representation method for many signals, has been recently employed in speech enhancement. This paper presents a new learning-based speech enhancement algorithm via sparse representation in the wavelet packet transform domain. We propose sparse dictionary learning procedures for training data of speech and noise signals based on a coherence criterion, for each subband of decomposition level. Using these learning algorithms, self-coherence between atoms of each dictionary and mutual coherence between speech and noise dictionary atoms are minimized along with the approximation error. The speech enhancement algorithm is introduced in two scenarios, supervised and semi-supervised. In each scenario, a voice activity detector scheme is employed based on the energy of sparse coefficient matrices when the observation data is coded over corresponding dictionaries. In the proposed supervised scenario, we take advantage of domain adaptation techniques to transform a learned noise dictionary to a dictionary adapted to noise conditions captured based on the test environment circumstances. Using this step, observation data is sparsely coded, based on the current situation of the noisy space, with low sparse approximation error. This technique has a prominent role in obtaining better enhancement results particularly when the noise is non-stationary. In the proposed semi-supervised scenario, adaptive thresholding of wavelet coefficients is carried out based on the variance of the estimated noise in each frame of different subbands. The proposed approaches lead to significantly better speech enhancement results in comparison with the earlier methods in this context and the traditional procedures, based on different objective and subjective measures as well as a statistical test.