The processing mechanism of the human brain for speech information is a significant source of inspiration for the study of speech enhancement technology. Attention and lateral inhibition are key mechanisms in auditory information processing that can selectively enhance specific information. Building on this, the study introduces a dual-branch U-Net that integrates lateral inhibition and feedback-driven attention mechanisms. Noisy speech signals input into the first branch of the U-Net led to the selective feedback of time-frequency units with high confidence. The generated activation layer gradients, in conjunction with the lateral inhibition mechanism, were utilized to calculate attention maps. These maps were then concatenated to the second branch of the U-Net, directing the network’s focus and achieving selective enhancement of auditory speech signals. The evaluation of the speech enhancement effect was conducted by utilising five metrics, including perceptual evaluation of speech quality. This method was compared horizontally with five other methods: Wiener, SEGAN, PHASEN, Demucs and GRN. The experimental results demonstrated that the proposed method improved speech signal enhancement capabilities in various noise scenarios by 18% to 21% compared to the baseline network across multiple performance metrics. This improvement was particularly notable in low signal-to-noise ratio conditions, where the proposed method exhibited a significant performance advantage over other methods. The speech enhancement technique based on lateral inhibition and feedback-driven attention mechanisms holds significant potential in auditory speech enhancement, making it suitable for clinical practices related to artificial cochleae and hearing aids.
Objective To study the correlation between smoking and obstructive sleep apnea (OSA). Methods A total of 454 patients from October 2015 to July 2021 were retrospectively collected for nocturnal polysomnography monitoring (no less than 7 hours). The patients were divided into an OSA group (n=405) and a control group (n=49, patients with primary snoring) according to the results of polysomnography monitoring. According to the apnea hypopnea index (AHI) and the lowest oxygen saturation during sleep, the severity of OSA was classified into a mild to moderate group (5 times/h ≤ AHI<30 times/h) and a severe group (AHI ≥30 times/h). The patients were inquired about their smoking history, then the patients diagnosed with OSA were further divided into a smoking group, a smoking cessation group, and a non-smoking group based on their smoking history. Results The smoking rate of the patients in the OSA group was higher than that in the control group (50.9% vs. 32.7%, P<0.05), while the smoking rate in the severe OSA group was higher than that in the mild to moderate group (55.7% vs. 39.8%, P<0.05). Smoking was positively correlated with AHI, cumulative percentages of time spent at oxygen saturation below 90% (Ts90%), and total apnea time (r value was 0.196, 0.197, 0.163, P<0.05), while negatively correlated with the lowest and average SpO2 during sleep (r value was –0.202, –0.214, P<0.05). The logistic regression analysis with severe OSA as the outcome variable showed that smoking (OR=1.781) and obesity (OR=1.930) were independent risk factors of severe OSA (P<0.05). The comparison between groups of the OSA patients with different smoking states showed that the proportion of severe OSA, AHI, Ts90%, and total apnea time (77.8%, 53.55 times/h, 18.35%, and 111.70 minutes, respectively) of the smoking group were higher than those of the non-smoking group (62.8%, 40.20 times/h, 8.40%, and 76.20 minutes, respectively, P<0.05). The lowest SpO2 and average SpO2 during sleep (69.50%, 93.00%, respectively) of the smoking group were lower than those of the non-smoking group (75.00%, 94.00%, respectively, both P<0.05). The average SpO2 of the smoking cessation group was higher than that of the smoking group (94.00% vs. 93.00%, P<0.05), and the Ts90% of the smoking cessation group was lower than that of the smoking group (6.75% vs. 18.35%, P<0.05). Conclusions Smoking significantly affects the degree of sleep-disordered breathing and may be an independent risk factor for severe OSA. Smoking can exacerbate the severity of OSA and the degree of hypoxia, while smoking cessation can improve the degree of hypoxia in OSA patients.