Speech Spectral Subtraction in Modulation Domain

Abajaddi, Nesrine; Mounir, Badia; Elmaazouzi, Laila; Mounir, Ilham; Farchi, Abdelmajid

doi:10.1007/978-3-030-91738-8_23

Cited by 2 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…IMMII Laboratory, Faculty of Sciences & Technics, Hassan First University, Settat, Morocco n.abajaddi@uhp.ac.ma have been proposed, including applying a half-wave rectifier and setting all negative values to zero [12][13][14]. Another approach is to use an over-reduction factor and a spectral floor factor, but speech may be distorted and consequently lead to a loss of intelligibility [15,16]. Due to the varying spectral distribution of the signal and noise across different frequency ranges, researchers have directed their attention toward subband processing methods.…”

Section: Nesrine Abajaddimentioning

confidence: 99%

A robust speech enhancement method in noisy environments

Abajaddi,

Elfahm,

Mounir

et al. 2023

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

Speech enhancement aims to eliminate or reduce undesirable noises and distortions, this processing should keep features of the speech to enhance the quality and intelligibility of degraded speech signals. In this study, we investigated a combined approach using single-frequency filtering (SFF) and a modified spectral subtraction method to enhance single-channel speech. The SFF method involves dividing the speech signal into uniform subband envelopes, and then performing spectral over-subtraction on each envelope. A smoothing parameter, determined by the a-posteriori signal-to-noise ratio (SNR), is used to estimate and update the noise without the need for explicitly detecting silence. To evaluate the performance of our algorithm, we employed objective measures such as segmental SNR (segSNR), extended short-term objective intelligibility (ESTOI), and perceptual evaluation of speech quality (PESQ). We tested our algorithm with various types of noise at different SNR levels and achieved results ranging from 4.24 to 15.41 for segSNR, 0.57 to 0.97 for ESTOI, and 2.18 to 4.45 for PESQ. Compared to other standard and existing speech enhancement methods, our algorithm produces better results and performs well in reducing undesirable noises.

show abstract

Section: Nesrine Abajaddimentioning

confidence: 99%

A robust speech enhancement method in noisy environments

Abajaddi,

Elfahm,

Mounir

et al. 2023

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

show abstract

“…listen better. SE methods such as spectral subtraction [1], [2], Wiener filtering [3], and statistical [4], [5] have been proposed in the last few decades. These methods were computationally efficient but inadequate in dealing with nonstationary noises.…”

Section: Introductionmentioning

confidence: 99%

U-Shaped Low-Complexity Type-2 Fuzzy LSTM Neural Network for Speech Enhancement

et al. 2023

View full text Add to dashboard Cite

Speech enhancement (SE) aims to improve the intelligibility and perceptual quality of speech contaminated by noise signals through spectral or temporal changes. Deep learning models achieve speech enhancement and estimate the magnitude spectrum. This paper proposes a novel and computationally efficient deep learning model to enhance noisy speech. The model pre-processes the noisy speech magnitude by redistributing energy from high-energy voiced segments to low-energy unvoiced segments using an adaptive power law transformation while maintaining the total energy of the speech signals constant. A U-shaped fuzzy long short-term memory (UFLSTM) estimates the magnitude of a time-frequency (T-F) mask by using the pre-processed data. Residual connections to the similar-shaped layers are added to avoid gradient decay. Attention process is adopted by modifying the forget gate of UFLSTM. To make a causal speech enhancement system, the processing does not include any future audio frames. We compare the proposed speech enhancement to other deep learning models in different noisy environments with signal-to-noise ratios of 0 dB, 5 dB, and 10 dB. The experiments show that the proposed SE system outscores the competing deep learning models and considerably improves speech intelligibility and quality. In terms of STOI and PESQ, the LibriSpeech database improves results by (0.211) 21.1% and (0.95) 36.39%, respectively, over noisy speech in seen noisy conditions, and by (0.199) 19.9% and (0.94) 35.69% over noisy speech in unseen noisy conditions. Further, the cross-corpus analysis shows that proposed SE system performs better when trained with the DNS dataset as compared to the LibriSpeech, VoiceBank, and TIMIT datasets.

show abstract

Speech Spectral Subtraction in Modulation Domain

Cited by 2 publications

References 10 publications

A robust speech enhancement method in noisy environments

A robust speech enhancement method in noisy environments

U-Shaped Low-Complexity Type-2 Fuzzy LSTM Neural Network for Speech Enhancement

Contact Info

Product

Resources

About