INFERRING SOCIAL CONTEXTS FROM AUDIO RECORDINGS USING DEEP NEURAL NETWORKS
Meysam Asgari1, Izhak Shafran1, Alireza Bayestehtashk1
1Center for Spoken Language Understanding, Oregon Health & Science University.
IEEE International Workshop on Machine Learning for Signal Processing : [Proceedings]. IEEE International Workshop on Machine Learning for Signal Processing
|March 8, 2021
Summary
This study introduces a novel method for detecting social contexts from everyday audio recordings, even with significant background noise. The approach uses unsupervised feature extraction and supervised classification for improved accuracy in real-world applications.
Area of Science:
- Computer Science
- Signal Processing
- Machine Learning
Background:
- Everyday audio recordings, like those in life-logs, present unique challenges for social context detection due to diverse background noise.
- Collecting and labeling extensive noise data for fully supervised learning is often impractical for real-world applications.
Purpose of the Study:
- To develop an effective method for detecting social contexts from noisy, everyday audio recordings.
- To address the limitations of supervised learning when labeled data is scarce.
Main Methods:
- Utilized unsupervised feature extraction with sparse auto-encoders to handle varied noise conditions.
- Employed supervised learning for a social context classifier following feature extraction.
- Investigated various model training strategies.
Main Results:
- Demonstrated the efficacy of unsupervised feature extraction for noisy audio data.
- Achieved successful social context detection in a real-world application scenario.
- Identified optimal strategies for training the combined unsupervised-supervised models.
Conclusions:
- The proposed approach of combining unsupervised feature extraction and supervised classification is effective for social context detection in challenging audio environments.
- This method offers a viable solution for analyzing real-world audio data where labeled examples are limited.
Related Concept Videos
01:21Impact of Social Context on Individuals
162
Social psychology examines how the real or imagined presence of others influences individuals' thoughts, feelings, and behaviors. A key concept in this field is the role of social context in shaping behavior. The same individual may act differently depending on the social setting, due to the varying expectations and norms associated with each environment. This context-dependent behavior illustrates the influence of social roles, which prescribe appropriate conduct in specific situations.Social...
162
01:21Perceiving Loudness, Pitch, and Location
633
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...
633
01:29Introducing Social Perception
148
Perceiving others accurately is fundamental to effective communication and relationship-building. Social perception, a key concept in social psychology, refers to the cognitive processes through which individuals gather and interpret information about others to understand their actions, intentions, and motivations. This process extends beyond spoken words and overt behaviors, incorporating subtle nonverbal cues and contextual factors.Nonverbal Cues and Their SignificanceNonverbal cues play a...
148
01:17Auditory Perception
781
The auditory system is essential for sound perception, utilizing various critical structures. When sound waves enter the outer ear, they travel through the ear canal and cause the eardrum to vibrate. These vibrations are then transmitted to the middle ear, where three tiny bones – the malleus, incus, and stapes – amplify the sound. This amplification is crucial, as it ensures that the sound vibrations are strong enough to be conveyed to the inner ear. These vibrations then reach the...
781
01:25Neural Circuits
2.1K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
2.1K
01:31Hearing
55.1K
When we hear a sound, our nervous system is detecting sound waves—pressure waves of mechanical energy traveling through a medium. The frequency of the wave is perceived as pitch, while the amplitude is perceived as loudness.
55.1K