密集连接的卷积循环网络用于噪音语音中的基本频率估计.
Yixuan Zhang1, Heming Wang1, DeLiang Wang1,2
1Department of Computer Science and Engineering, The Ohio State University, USA.
Interspeech
|May 2, 2025
概括
这项研究引入了一种新的深度学习模型,用于在杂的语音中进行基本频率 (F0) 估计. 拟议的级联模型提高了F0估计的准确性,特别是在具有挑战性的低信号噪声比条件下.
科学领域:
- 语音处理 语音处理
- 机器学习是机器学习.
- 信号分析 信号分析
背景情况:
- 准确的基本频率 (F0) 估计对于语音合成和分析至关重要.
- 从杂的语音中估计F0仍然具有挑战性,因为噪音会破坏语音的和声结构.
研究的目的:
- 使用深度学习开发一种强大的F0估计方法,用于使用深度学习的杂语音.
- 调查语音增强对F0估计准确性的影响.
- 在不利的声学条件下提出一个级联模型,以改进F0估计.
主要方法:
- 将F0估计作为一个多类分类问题.
- 使用频域密集连接的卷积神经网络 (DC-CRN).
- 将复杂的短时间里叶变换 (STFT) 与大小STFT作为输入特征进行比较.
- 开发一个级联模型,集成语音增强和F0估计模块.
主要成果:
- 在F0检测率方面,DC-CRN模型显著优于基线方法.
- 复杂的STFT输入产生了比大小STFT更好的性能.
- 综合语音增强的级联模型进一步提高了F0估计的准确性.
- 级联模型在低信号噪声比 (SNR) 的环境中显示了特殊的好处.
结论:
- 深度学习,特别是DC-CRN,提供了一种强大的方法,用于在杂的语音中估计F0.
- 语音增强,当有效地集成到级联模型中时,可以提高F0估计性能.
- 拟议的级联模型提供了一个有希望的解决方案,用于在各种噪声条件下进行可靠的F0估计.
相关概念视频
01:26Linear Approximation in Frequency Domain
79
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
79
01:08Determination of Expected Frequency
2.1K
Suppose one wants to test independence between the two variables of a contingency table. The values in the table constitute the observed frequencies of the dataset. But how does one determine the expected frequency of the dataset? One of the important assumptions is that the two variables are independent, which means the variables do not influence each other. For independent variables, the statistical probability of any event involving both variables is calculated by multiplying the individual...
2.1K
01:21Perceiving Loudness, Pitch, and Location
160
The human brain perceives pitch through two primary mechanisms reflected in place theory and frequency theory. Each mechanism describes how sound waves are interpreted as specific pitches by the brain, offering insights into the intricate processes of auditory perception.
Place theory, or place coding, suggests that different pitches are heard because various sound waves activate specific locations along the cochlea's basilar membrane. The brain determines the pitch of a sound by...
Place theory, or place coding, suggests that different pitches are heard because various sound waves activate specific locations along the cochlea's basilar membrane. The brain determines the pitch of a sound by...
160
01:11Sampling Continuous Time Signal
176
In signal processing, a continuous-time signal can be sampled using an impulse-train sampling technique, followed by the zero-order hold method. Impulse-train sampling involves the use of a periodic impulse train, which consists of a series of delta functions spaced at regular intervals determined by the sampling period. When a continuous-time signal is multiplied by this impulse train, it generates impulses with amplitudes corresponding to the signal's values at the sampling points.
In the...
In the...
176
01:30Classification of Signals
314
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
314
01:11Continuous -time Fourier Transform
237
The Fourier series is instrumental in representing periodic functions, offering a powerful method to decompose such functions into a sum of sinusoids. This technique, however, necessitates modification when applied to nonperiodic functions. Consider a pulse-train waveform consisting of a series of rectangular pulses. When these pulses have a finite period, they can be accurately represented by a Fourier series. Yet, as the period approaches infinity, resulting in a single, isolated pulse, the...
237