A hybrid speech enhancement system with DNN based speech reconstruction and Kalman filtering

Yu, Hongbo; Zhu, Wei-Ping; Ouyang, Zhiheng; Champagne, Benoı̂t

doi:10.1007/s11042-020-09563-5

Cited by 3 publications

(1 citation statement)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, speech recognition may yield low speech recognition accuracy especially at low signal-to-noise ratio (SNR) and nonstationary noise, which the quality and intelligibility of speech are affected [2]. Thus, past studies proposed the Deep Neural Network (DNN)-based mask estimation approach to guarantee high intelligibility and quality of speech signal [3][4][5][6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Approach for Single Channel Speech Enhancement using Deep Neural Network and Harmonic Regeneration Noise Reduction

Jamal¹,

Fuad²,

Sha’abani³

2020

IJACSA

View full text Add to dashboard Cite

This paper presents a hybrid approach for single channel speech enhancement using deep neural network (DNN) and harmonic regeneration noise reduction (HRNR). The DNN was used as a supervised algorithm to predict new target mask such as constrained Wiener Filter (cWF) target mask from noisy mixture signal that was transformed into gammatone filter bank features. Meanwhile, HRNR algorithm was applied in the postfiltering strategy to eliminate residual noise. The DNN algorithm is an emerging supervised speech enhancement to overcome heavy nonstationary noise and low signal-to-noise ratio (SNR) issues. To validate the proposed algorithm with new target mask, 600 Malay utterances combining male and female speakers were used in a training session while 120 Malay utterances were used in a prediction session. The short time objective intelligibility (STOI) and perceptual evaluation of speech quality (PESQ) scores were calculated as the performance metrics. In this work, the proposed target mask outperformed other baseline target masks. Thus, PESQ and STOI scores for the hybrid speech enhancement algorithm is 1.17 and 0.79, respectively, at -5 dB babble noise SNR.

show abstract