[用于听觉语音增强的神经网络,具有反驱动的注意力和侧向抑制]
Yudong Cai1, Xue Liu2, Xiang Liao3
1Guangxi Key Laboratory of Special Biomedicine & Advanced Institute for Brain and Intelligence, School of Medicine, Guangxi University, Nanning 530004, P. R. China.
概括
这项研究介绍了一种新的语音增强方法,灵感来自于大脑处理,使用侧向抑制和注意力机制. 该技术显著提高了语音清晰度,特别是在杂的环境中,有利于助听器和耳植入物用户.
科学领域:
- 听觉神经科学 听觉神经科学
- 信号处理 信号处理
- 人工智能的人工智能
背景情况:
- 人类大脑处理语音涉及注意力和侧向抑制,用于选择性增强.
- 现有的语音增强技术可以通过结合生物听觉处理机制来改进.
研究的目的:
- 开发一种先进的语音增强技术,灵感来自神经处理.
- 将侧向抑制和反驱动的注意力机制集成到双分支U-Net架构中.
主要方法:
- 设计了一个双分支U-Net模型,结合了横向抑制和反驱动的注意力.
- 处理了杂的语音,高可信度的时间频率单元被选择性地反.
- 使用激活层梯度和横向抑制生成注意力图,指导网络的增强.
主要成果:
- 拟议的方法在各种噪音条件下显著改善了语音增强,表现优于基线和其他先进方法.
- 与基线网络相比,在多个指标上,性能增长幅度从18%到21%不等.
- 在低信号噪声比条件下观察到显著的优势.
结论:
- 开发的语音增强技术有效地利用侧向抑制和注意力机制,用于高级听觉信号处理.
- 这种方法在临床环境中具有很强的实际应用潜力,包括人工带和助听器.
相关概念视频
Hearing
51.8K
When we hear a sound, our nervous system is detecting sound waves—pressure waves of mechanical energy traveling through a medium. The frequency of the wave is perceived as pitch, while the amplitude is perceived as loudness.
51.8K
Auditory Pathway
4.6K
Auditory pathways constitute the complex neural circuits responsible for transmitting and interpreting auditory information from the peripheral auditory system to the brain. Sound waves are initially captured by the outer ear, funneled through the ear canal, and reach the tympanic membrane (eardrum). These vibrations are transmitted via the middle ear's ossicles to the inner ear's cochlea.
When viewed cross-sectionally, the cochlea reveals the scala vestibuli and scala tympani flanking...
When viewed cross-sectionally, the cochlea reveals the scala vestibuli and scala tympani flanking...
4.6K
Effects of feedback
505
Feedback in control systems plays a critical role in shaping various operational parameters, extending beyond simple error reduction to influence stability, bandwidth, gain, impedance, and sensitivity. Understanding these effects requires examining a basic feedback system characterized by defined input, output, error, and feedback signals.
Feedback significantly modifies the gain of a control system. The gain of a system without feedback is altered by a factor of one plus GH, where G represents...
Feedback significantly modifies the gain of a control system. The gain of a system without feedback is altered by a factor of one plus GH, where G represents...
505
The Cochlea
44.4K
The cochlea is a coiled structure in the inner ear that contains hair cells—the sensory receptors of the auditory system. Sound waves are transmitted to the cochlea by small bones attached to the eardrum called the ossicles, which vibrate the oval window that leads to the inner ear. This causes fluid in the chambers of the cochlea to move, vibrating the basilar membrane.
44.4K


