Related Experiment Video
Updated: May 22, 2026
05:48
Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis
Published on: August 9, 2024
A frequency bin-wise nonlinear masking algorithm in convolutive mixtures for speech segregation.
Tai-Shih Chi1, Ching-Wen Huang, Wen-Sheng Chou
1Department of Electrical Engineering, National Chiao Tung University, Hsinchu 300, Taiwan. tschi@mail.nctu.edu.tw
The Journal of the Acoustical Society of America
|May 8, 2012
Summary
This study introduces a novel nonlinear masking algorithm for separating speech in complex sound mixtures. The method effectively extracts individual speech signals, outperforming existing techniques in simulations.
Area of Science:
- Signal Processing
- Acoustics
- Machine Learning
Background:
- Speech segregation in convolutive mixtures is challenging.
- Existing methods like ICA and DUNT have limitations.
Purpose of the Study:
- To propose a novel frequency bin-wise nonlinear masking algorithm for speech segregation.
- To improve the extraction of individual speech sources from convolutive mixtures.
Main Methods:
- Estimating contributive weights using a nonlinear function based on location cues.
- Generating non-binary masks for each source.
- Multiplying masks to mixture spectrograms for source extraction.
- Simulating convolutive mixtures using Head-Related Transfer Functions (HRTFs).
Main Results:
- The proposed nonlinear masking algorithm significantly outperforms convolutive Independent Component Analysis (ICA) and Degenerate Unmixing and Estimation Technique (DUET).
- Superior performance was observed across nearly all tested conditions.
Conclusions:
- The developed algorithm offers a more effective approach to speech segregation in convolutive mixtures.
- Location cues and nonlinear masking are crucial for accurate source separation.
Related Concept Videos
01:19Masking and Demasking Agents
EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on the metal...
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on the metal...
01:26Linear Approximation in Frequency Domain
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.
01:30Classification of Signals
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...
01:10Reconstruction of Signal using Interpolation
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next sampling...
01:20Deconvolution
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
01:14Extraction: Partition and Distribution Coefficients
The distribution law or Nernst's distribution law is the law that governs the distribution of a solute between two immiscible solvents. This law, also known as the partition law, states that if a solute is added to the mixture of two immiscible solvents at a constant temperature, the solute is distributed between the two solvents in such a way that the ratio of solute concentrations in the solvents remains constant at equilibrium.
For extracting a solute from an aqueous phase into an organic...
For extracting a solute from an aqueous phase into an organic...