Mechanical noise suppression based on non-negative matrix factorization and multi-band spectral subtraction for digital cameras

Jeon, Kwang Myung; Park, Nam In; Kim, Hong Kook; Choi, Myung Kyu; Hwang, Kwang Il

doi:10.1109/tce.2013.6531109

Cited by 6 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For those approaches, it is usually assumed that the sources are statistically independent and the noise is more stationary than the target signal. The recently well-studied model-based NMF approaches [5][6][7] can be used directly for noise reduction [46,47] or for noise estimation [48]. Those methods usually rely on the prior knowledge of the noise type (point source or diffuse noise) to define the model parameters.…”

Section: Comparison To Alternative Approachesmentioning

confidence: 99%

Analysis of dual-channel ICA-based blocking matrix for improved noise estimation

Zheng

Reindl

Kellermann

2014

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

For speech enhancement or blind signal extraction (BSE), estimating interference and noise characteristics is decisive for its performance. For multichannel approaches using multiple microphone signals, a BSE scheme combining a blocking matrix (BM) and spectral enhancement filters was proposed in numerous publications. For such schemes, the BM provides a noise estimate by suppressing the target signal only. The estimated noise reference is then used to design spectral enhancement filters for the purpose of noise reduction. For designing the BM, 'Directional Blind Source Separation (BSS)' was already proposed earlier. This method combines a generic BSS algorithm with a geometric constraint derived from prior information on the target source position to obtain an estimate for all interfering point sources and diffuse background noise. In this paper, we provide a theoretical analysis to show that Directional BSS converges to a relative transfer function (RTF)-based BM. The behavior of this informed signal separation scheme is analyzed and the blocking performance of Directional BSS under various acoustical conditions is evaluated. The robustness of Directional BSS regarding the localization error for the target source position is verified by experiments. Finally, a BSE scheme combining Directional BSS and Wiener-type spectral enhancement filters is described and evaluated.

show abstract

Section: Comparison To Alternative Approachesmentioning

confidence: 99%

Analysis of dual-channel ICA-based blocking matrix for improved noise estimation

Zheng

Reindl

Kellermann

2014

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

show abstract

“…In order to enhance speech signals recorded under such noise conditions, noise spectral components should be suppressed without damaging spectral components belonging to the target speech signal [3]. To this end, conventional efforts have been focused on estimating noise power spectra from the noisy signal [4,5] or separating speech and noise from the noisy speech [6][7][8][9][10][11][12][13][14][15] Among the successful noise estimation methods is the minima-controlled recursive algorithm (MCRA) [4,5]. MCRA estimates noise by only tracking minimum statistics in noise-only regions.…”

Section: Introductionmentioning

confidence: 99%

“…That is, noise-only regions are detected when the ratio between the noisy speech power spectrum and the minimum power spectrum is below a pre-defined threshold. However, the main drawback of MCRA is that non-stationary noises, such as harmonic or tonal noises, are difficult to estimate because their sparse characteristics in time and/or frequency are not suitable to be modelled by using only minimum statistics [6]. Thus, speech enhancement methods for use with challenging real environmental noises should consider both stationary and non-stationary characteristics of noise.…”

Section: Introductionmentioning

confidence: 99%

Local Sparsity Based Online Dictionary Learning for Environment-Adaptive Speech Enhancement with Nonnegative Matrix Factorization

Jeon¹,

Kim²

2016

Interspeech 2016

View full text Add to dashboard Cite

In this paper, a nonnegative matrix factorization (NMF)-based speech enhancement method robust to real and diverse noise is proposed by online NMF dictionary learning without relying on prior knowledge of noise. Conventional NMF-based methods have used a fixed noise dictionary, which often results in performance degradation when the NMF noise dictionary cannot cover noise types that occur in real-life recording. Thus, the noise dictionary needs to be learned from noises according to the variation of recording environments. To this end, the proposed method first estimates noise spectra and then performs online noise dictionary learning by a discriminative NMF learning framework. In particular, the noise spectra are estimated from minimum mean squared error filtering, which is based on the local sparsity defined by a posteriori signal-to-noise ratio (SNR) estimated from the NMF separation of the previous analysis frame. The effectiveness of the proposed speech enhancement method is demonstrated by adding six different realistic noises to clean speech signals with various SNRs. Consequently, it is shown that the proposed method outperforms comparative methods in terms of signal-to-distortion ratio (SDR) and perceptual evaluation of speech quality (PESQ) for all kinds of simulated noise and SNR conditions.

show abstract

“…Speech signal processing techniques have been developed in various ways such as signal enhancement [1][2][3][4][5], signal transmission over wireless network [6], speech recognition, and synthesis [7][8] to meet demanding of numerous speech-based applications. Among these techniques, speech synthesis is one of the important tasks because most applications including speech-based user interface requires various kinds of voices to be generated by a single textto-speech (TTS) system [8].…”

Section: Introductionmentioning

confidence: 99%

HMM-Based Distributed Text-to-Speech Synthesis Incorporating Speaker-Adaptive Training

Jeon¹,

Choi²

2014

IJMUE

View full text Add to dashboard Cite

In this paper, a hidden Markov model (HMM) based distributed text-to-speech (TTS) system is proposed to synthesize the voices of various speakers in a client-server framework. The proposed system is based on speaker-adaptive training for constructing HMMs corresponding to a target speaker, and its computational complexity is balanced by distributing the processing modules of the TTS system at both the client and server to achieve a real-time operation. In other words, fewer complex operations, such as text inputs and HMM-based speech synthesis, are conducted by the client, while speaker-adaptive training, which is a very complex operation, is assigned to the server. It is shown from performanceevaluation that the proposed TTS system operates in real time and provides good synthesized speech quality in terms of intelligibility and similarity.

show abstract

Mechanical noise suppression based on non-negative matrix factorization and multi-band spectral subtraction for digital cameras

Cited by 6 publications

References 19 publications

Analysis of dual-channel ICA-based blocking matrix for improved noise estimation

Analysis of dual-channel ICA-based blocking matrix for improved noise estimation

Local Sparsity Based Online Dictionary Learning for Environment-Adaptive Speech Enhancement with Nonnegative Matrix Factorization

HMM-Based Distributed Text-to-Speech Synthesis Incorporating Speaker-Adaptive Training

Contact Info

Product

Resources

About