Related Experiment Video
Updated: Jul 12, 2025
05:48
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
Published on: August 9, 2024
1.5K
Attentive Training: A New Training Framework for Speech Enhancement.
Ashutosh Pandey1, DeLiang Wang2
1Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210 USA.
IEEE/ACM Transactions on Audio, Speech, and Language Processing
|October 30, 2023
Summary
This study introduces Attentive Training, a new method to improve speech enhancement systems by focusing on the first speaker in noisy environments. This approach effectively handles speech interruptions in single-output systems.
Area of Science:
- Speech processing
- Deep learning
- Signal processing
Background:
- Speech enhancement systems often struggle with multiple speakers and noise.
- Existing methods like speaker separation or extraction have limitations for single-output systems.
Purpose of the Study:
- To propose a novel training framework, Attentive Training, for speech enhancement systems.
- To enable speech enhancement systems to effectively handle speech interruptions from multiple speakers.
Main Methods:
- Developed a novel training framework named Attentive Training.
- Trained a deep neural network to represent and track the first speaker in a noisy mixture.
Main Results:
- Demonstrated the effectiveness of Attentive Training for speech enhancement.
- Showcased the ability to attend to and track a target speaker in multitalker noisy conditions.
Conclusions:
- Attentive Training is a viable solution for enhancing speech in the presence of interruptions.
- The proposed method is suitable for standalone speech enhancement systems with a single output stream.
Related Concept Videos
01:27Air-entraining Agents
81
Air-entraining agents improve the durability and workability of concrete in climates with frequent freezing and thawing. These agents prevent cracks by introducing small air bubbles into the mix, creating spaces accommodating water expansion when temperatures drop. The air-entraining agents lower the surface tension of water, forming stable, small air bubbles. This method is more effective than having accidental large voids, as the intentional, smaller, and evenly distributed air voids improve...
81
01:21Perceiving Loudness, Pitch, and Location
220
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...
220