减少算法延迟对基于深度学习的降噪的感知效应)
Eric W Healy1,2, Sarah E Yoho1,2, Kian Fallah1
1Department of Speech and Hearing Science, The Ohio State University, Columbus, Ohio 43210, USA.
The Journal of the Acoustical Society of America
|July 14, 2025
概括
降低用于助听器降噪的深度神经网络延迟并没有影响人类听众的语音可理解性. 这一发现对于开发有效的,低延迟的降噪系统至关重要.
科学领域:
- 听觉神经科学 听觉神经科学
- 信号处理 信号处理
- 机器学习 机器学习
背景情况:
- 低延迟对于助听器的实时降噪至关重要.
- 深度神经网络 (DNN) 提供先进的降噪,但可以引入延迟.
- 在实际应用中,平衡DNN性能与延迟是必不可少的.
研究的目的:
- 研究基于DNN的降噪系统中算法延迟和语音可理解性之间的权衡.
- 确定降低延迟对专心循环网络 (ARN) 性能的影响.
- 在降噪场景中为人类听众建立延迟要求.
主要方法:
- 通过改变分析时间框架,修改了一个完全因果关系的,与说话者独立的RNA的算法延迟.
- 在各种信号噪声比率 (SNRs) 上评估了RNA在语中的句子上的降噪性能.
- 通过与正常听力和听力损失的参与者进行听力测试来评估语音可理解性.
主要成果:
- 通过降低噪音,在语音可理解性方面取得了显著的改进,特别是在听力损失的听众和较低的SNR中.
- 目标网络性能指标显示,随着延迟的增加,网络性能略有改善.
- 最重要的是,人类语音可理解性基本上不受影响,因为算法延迟时间从20到10或5毫秒减少.
结论:
- 在基于DNN的降噪系统中减少算法延迟是可行的,而不会影响用户的语音可理解性.
- 这项研究为有效的助听器和耳植入物设计的延迟要求提供了宝贵的见解.
- 这些发现支持开发用于听觉设备的低延迟,高性能降噪解决方案.
相关概念视频
01:18Reducing Line Loss
196
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
196
01:20Downsampling
257
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
257
01:05Difference from Background: Limit of Detection
7.1K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
The LOD indicates the presence or absence...
7.1K
01:22Upsampling
319
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
319
01:15Subliminal Perception
365
Subliminal perception refers to the processing of sensory information that occurs below the level of conscious awareness. Researchers study subliminal perception by presenting a stimulus, such as a word or image, very quickly, typically around 50 milliseconds. This rapid presentation is often followed by another stimulus, such as a pattern of dots or lines, which blocks further mental processing of the initial stimulus. As a result, if participants cannot identify the initial stimulus better...
365