Speech enhancement by combining spectral subtraction and minimum mean square error-spectrum power estimator based on zero crossing

Yadava, Thimmaraja G.; Jayanna, H. S.

doi:10.1007/s10772-018-9506-9

Cited by 26 publications

(7 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Boll in [27], Kamath and Loizou [28], Jounghoon and Hanseok[26], Cole et al [29] and Goodarzi and Seyedtabaii [29] suggested the SSVAD technique for speech enhancement. The effect of noise can be removed from the signal by deducting the average magnitude spectrum of the noise model from the average magnitude spectrum of the degraded audio signal [30]. VAD is used to determine the voice activity sections in the degraded speech data [31].…”

Section: Spectral Subtraction Ltermentioning

confidence: 99%

Discrete Wavelet Transform and Spectral Subtraction Based Speech Enhancement Algorithm for Hearing Aid Application

Iqbal,

Zhang,

Geng

et al. 2024

Preprint

View full text Add to dashboard Cite

Hearing aids are small electronic devices intended to help those with hearing loss improve their hearing ability with the use of advanced audio signal processing techniques and technologies. Usually, in hearing aids, a set of speech enhancement methods are utilized to improve speech signal quality in low signal-to-noise ratio (SNR) environments. In speech processing, Discrete Wavelet Transform (DWT) algorithm and Spectral Subtraction (SS) filter are some of the most commonly used methods today when handling background noise in hearing aids. However, these speech enhancement systems have drawbacks like in DWT, the selective thresholding face problems when applying to distinct types of noise with different frequencies and time scales, and spectral subtraction has a problem with music noise, which affects the denoising performance. In this paper, the Spectral Subtraction (SS) filter and DWT speech enhancement methods are combined to deal with problem faced by DWT selective thresholding techniques against noise of different frequencies and time scales and the musical noise faced by the spectral subtraction filter. We first used spectral subtraction to reduce average noise intensity and then added DWT thresholding for reducing the background noise further. The contemporary methods evaluated using English speech signals taken from CSTR VCTK Corpus database. The objective metrics used to evaluate proposed speech enhancement systems are MSE, SNR, PESQ, and STOI. The proposed speech enhancement algorithm is applied for noise reduction and then compared with conventional algorithms. Experimental results prove that using of the proposed speech enhancement algorithm reduces background noise, improves the SNR of an original speech signal, and improves the final noise reduction performance.

show abstract

Section: Spectral Subtraction Ltermentioning

confidence: 99%

Discrete Wavelet Transform and Spectral Subtraction Based Speech Enhancement Algorithm for Hearing Aid Application

Iqbal,

Zhang,

Geng

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…At last, to maintain the image contour of the targets, the minimum mean square error (MMSE) method [32]- [34] is used to smooth the edge. Using the frequencies of the detected edge, the estimated pitch velocity ( v cos ϕ) of the forwardlooking targets at different range bins can be calculated by ( 3).…”

Section: ) Smooth the Edge By Curve Fittingmentioning

confidence: 99%

Doppler Beam Sharpening Using Estimated Doppler Centroid Based on Edge Detection and Fitting

Mao¹,

Zhang²,

Huang³

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Doppler beam sharpening (DBS) technology is widely used in applications, such as helicopter rescue and early warning surveillance. To obtain the desired DBS images with high quality, accurate Doppler centroid estimation (DoCE) is necessary. Conventional methods for Doppler centroid estimation based on navigational devices are sensitive to the errors of the measured motion parameters. Hence, several alternative data-depended approaches have been developed to reduce the error. In this paper, a novel data-depended Doppler centroid estimation method is proposed to improve the image quality of DBS. We begin the method by analyzing the characteristics of range-Doppler distribution in different regions of interests. Then, the edge feature of range-Doppler distribution in forward-looking direction is extracted using morphological filtering and edge detection methods. We will show that the edge feature defines the required Doppler centroid parameters, which can be utilized to estimate the Doppler centroids of the full scene. At last, the estimation error is reduced through fitting the edge with the minimum mean square error (MMSE) algorithm. As compared with conventional Doppler centroid estimation methods, the proposed method can significantly provide reliable estimation accuracy under low echo signal to noise ratio, independent of conditions that strictly required by conventional methods. Simulations and experiments verify the proposed method.INDEX TERMS Doppler beam sharpening, Doppler centroid estimation, edge detection and fitting.

show abstract

“…In the history of Kannada language, for the first time, an end-to-end (E2E) ASR system was developed for accessing the real time commodity prices information and weather forecasting in Kannada language/dialects (11) and demonstrated the continuous advancements (12)(13)(14) in the performance of E2E ASR system in terms of speech recognition accuracy by proposing noise reduction algorithm (12) . Development of spoken-query-system (SQS) to recognize the Kannada continuous speech sentences was demonstrated in (15) .…”

Section: Introductionmentioning

confidence: 99%

“…The authors have achieved a WER of 4.64% using DNN-HMM. All our previous works (11)(12)(13)(14)(15)(16)(17) described the development of large vocabulary isolated and continuous E2E ASR systems for Kannada language/dialects. In this work, an attempt is made to develop a continuous speech-to-text system for small vocabulary for Kannada language/dialects.…”

Section: Introductionmentioning

confidence: 99%

Development of Small Vocabulary Continuous Speech-to-Text System for Kannada Language/Dialects

G¹,

Nagaraja²,

Kumaran³

et al. 2022

IJST

View full text Add to dashboard Cite

Objectives: To develop a speech-to-text (STT) system using Kaldi speech recognition toolkit for continuous Kannada language/dialects. Methods: A continuous Kannada speech data is collected from 100 speakers/farmers of Karnataka state in field. The lexicon/dictionary and set of phonemes for Kannada language/dialects are created and transcribed the collected speech data using transcriber tool. The ASR models are developed at different phoneme levels using Kaldi. Findings: In this work, an effort is made to develop a robust small vocabulary STT system for continuous Kannada language using Kaldi. The various acoustic modelling techniques are used to develop a robust ASR model and achieved a word error rate (WER) of 0.23%. The performance of the developed ASR model is compared with existing works and analyzed by offline speech recognition. Novelty: Many STT systems have been developed for Indian and International languages/dialects, but not for Kannada language. This work is first of its kind using Kaldi in Kannada language under the constraints of limited data. The developed ASR model could be used further in the development of end-to-end ASR system for speech processing applications.

show abstract

Speech enhancement by combining spectral subtraction and minimum mean square error-spectrum power estimator based on zero crossing

Cited by 26 publications

References 35 publications

Discrete Wavelet Transform and Spectral Subtraction Based Speech Enhancement Algorithm for Hearing Aid Application

Discrete Wavelet Transform and Spectral Subtraction Based Speech Enhancement Algorithm for Hearing Aid Application

Doppler Beam Sharpening Using Estimated Doppler Centroid Based on Edge Detection and Fitting

Development of Small Vocabulary Continuous Speech-to-Text System for Kannada Language/Dialects

Contact Info

Product

Resources

About