Non-negative Matrix Factorization Based Noise Reduction for Noise Robust Automatic Speech Recognition

Kim, Seon Man; Park, Ji Hun; Kim, Hong Kook; Lee, Sung Joo; Lee, Yun Keun

doi:10.1007/978-3-642-28551-6_42

Cited by 11 publications

(8 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where [14,15]. For givenS andD, BS and BD can be obtained through a multiplicative update rule [25] as…”

Section: Conventional Nmf-based Noisementioning

confidence: 99%

“…As an initial condition for (15), all elements of A 0 D can be set as random values between 0 and 1, whereas B 0 D = BD. Similar to the NMF training described in (4)- (7), the procedure of (15) …”

Section: Nmf-based Adaptive Noisementioning

confidence: 99%

“…In particular, recent research works have reported that NMF-based noise reduction methods have been successfully applied to a front-end of an ASR system under various nonstationary noise environments [14][15][16]. However, the performance of NMF-based noise reduction methods degraded substantially when there was a mismatch in noise type for noise basis training and estimation using NMF [17,18].…”

Section: Introductionmentioning

confidence: 99%

“…As an alternative, nonnegative matrix factorization (NMF)-based noise reduction methods have been proposed to estimate the noise spectrum effectively under nonstationary noise conditions [12][13][14][15][16]. In particular, recent research works have reported that NMF-based noise reduction methods have been successfully applied to a front-end of an ASR system under various nonstationary noise environments [14][15][16]. However, the performance of NMF-based noise reduction methods degraded substantially when there was a mismatch in noise type for noise basis training and estimation using NMF [17,18].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Nonnegative Matrix Factorization Based Adaptive Noise Sensing over Wireless Sensor Networks

Jeon

Kim

Lee

et al. 2014

International Journal of Distributed Sensor Networks

Self Cite

View full text Add to dashboard Cite

An adaptive noise sensing method is proposed to improve the speech sensing performance of speech-based applications operated over wireless sensor networks. The proposed method is based on nonnegative matrix factorization (NMF), which consists of adaptive noise sensing and noise reduction. In other words, adaptive noise sensing is performed by adapting a priori noise basis matrix of the NMF, which is estimated from the noise signal, resulting in an adapted noise basis matrix. Subsequently, the adapted noise basis matrix is used for the NMF decomposition of noisy speech into clean speech and background noise. The estimated clean speech signal is then applied to a front-end of the speech-based applications. The performance of the proposed NMF-based noise sensing and reduction method is first evaluated by measuring the source to distortion ratio (SDR), the source to interferences ratio (SIR), and the source to artifacts ratio (SAR). In addition, the proposed method is applied to an automatic speech recognition (ASR) system, which is a typical speech-based application, and then the average word error rate (WER) of the ASR is compared with that employing either a Wiener filter, or a conventional NMF-based noise reduction method using only a priori noise basis matrix.

show abstract

“…where [14,15]. For givenS andD, BS and BD can be obtained through a multiplicative update rule [25] as…”

Section: Conventional Nmf-based Noisementioning

confidence: 99%

Section: Nmf-based Adaptive Noisementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Nonnegative Matrix Factorization Based Adaptive Noise Sensing over Wireless Sensor Networks

Jeon

Kim

Lee

et al. 2014

International Journal of Distributed Sensor Networks

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, they may not accurately estimate non-stationary noises that occur in most real environments [3]. As an alternative, non-negative matrix factorization (NMF) based noise reduction methods have been proposed [4][5] to effectively estimate noise spectrum under non-stationary noise conditions. Nevertheless, the performance of the NMF-based noise estimation method can be limited depending on how accurately the noise basis matrix can be used to decompose a noisy signal into a clean and noise signals.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Noise Estimation Based on Non-negative Matrix Factorization

Jeon

Kim²

2013

IT Convergence and Its Applications

Self Cite

View full text Add to dashboard Cite

In this paper, an adaptive noise estimation technique is proposed on the basis of non-negative matrix factorization (NMF). As an initial step of the proposed method, the noise basis matrix of NMF is estimated from a collection of noise signals. Then, the proposed method updates the initially estimated noise basis matrix on the fly by using an estimate of the noise spectrum from the noisy signal. It is here demonstrated that the proposed method provides a better noise estimate than a NMF-based method without using any adaptation, especially when there is a mismatch in noise conditions for noise basis training and estimation using NMF.

show abstract