Related Experiment Video
Updated: Jul 14, 2026

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis
Published on: August 9, 2024
Speech enhancement using the modified phase-opponency model
Om D Deshmukh1, Carol Y Espy-Wilson, Laurel H Carney
1Department of Electrical and Computer Engineering and Institute for Systems Research, University of Maryland, College Park, Maryland 20742, USA. omdesh@glue.umd.edu
This study introduces the Modified Phase-Opponency (MPO) model for clearer speech enhancement in noisy conditions. The MPO model effectively reduces additive noise without needing to estimate noise characteristics, improving speech quality.
Area of Science:
- Auditory neuroscience
- Signal processing
- Speech technology
Background:
- Speech enhancement is crucial for audibility in noisy environments.
- Existing methods often require noise estimation or statistical assumptions.
- Auditory models offer biologically plausible approaches to signal processing.
Purpose of the Study:
- To present the Modified Phase-Opponency (MPO) model for single-channel speech enhancement.
- To adapt the auditory Phase-Opponency (PO) model for speech processing.
- To develop a noise-robust speech enhancement technique.
Main Methods:
- The Modified Phase-Opponency (MPO) model is based on the auditory PO model.
- It utilizes cross-auditory-nerve-fiber coincidence detection for temporal cue extraction.
- The MPO model allows independent analysis and modification of its components.
Main Results:
- The MPO-based scheme does not require noise characteristic estimation or statistical noise modeling.
- It achieved the lowest Linear Predictive Coding (LPC)-based objective measures.
- It resulted in the highest Perceptual Evaluation of Speech Quality (PESQ) scores for fluctuating noise.
- Integration with a pitch detector further enhanced performance.
Conclusions:
- The MPO model offers an effective and robust approach to speech enhancement.
- It outperforms other methods, particularly with fluctuating noise.
- The model provides a noise-unsupervised and statistically flexible speech enhancement solution.
Related Concept Videos
Interference: Path Lengths
Two special sources may be considered when they are in phase. This can be easily achieved by feeding the two sources from the same source. An example would be synchronizing the two speakers by feeding them with the same source, such as the sound waves produced by a tuning fork. This setup ensures that the two sources have the same frequency and are...
Sound Waves: Interference
Phase-lead and Phase-lag Controllers
Time and frequency -Domain Interpretation of Phase-lead Control
The design of phase-lead control involves the strategic placement of poles and zeros to balance steady-state error and system...
Perceiving Loudness, Pitch, and Location
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 identifying...
Facial Feedback Hypothesis
