Conversation Dependent Volume Control Using Speech Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to effectively reduce noise levels in environments when conversations occur, as they do not accurately detect conversations and adjust sound contributing devices accordingly, leading to distractions and audibility issues.
Innovation Solution
A system that detects conversations by analyzing audio signals using spectral analysis and speech models, identifying speech patterns and the Lombard effect to determine if speech is part of a conversation, and adjusts the operating state of sound contributing devices to reduce noise levels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If the volume of sound contributing devices is increased to overcome road noise at higher speeds, then the audio system becomes more audible, but conversation audibility deteriorates
Solution Approach 1:
The system continuously monitors the acoustic environment using microphones to detect speech patterns and conversation states. Based on this feedback, the volume control system dynamically adjusts the audio output level. When speech is detected indicating a conversation, the system automatically reduces volume to maintain conversation audibility while preventing road noise from overpowering the audio system at higher speeds.
Solution Approach 2:
The volume control system transitions from static speed-based volume adjustment to dynamic conversation-aware volume control. The system continuously adapts the audio volume based on real-time detection of conversation states, speech patterns, and acoustic environment changes, allowing the volume to be adjusted dynamically rather than following a fixed speed-based curve.
2Object-affected harmful factors
If the volume of sound contributing devices is decreased to improve conversation audibility, then conversation becomes more audible, but audio system effectiveness deteriorates
Solution Approach 1:
The system implements dynamic volume adjustment based on real-time conversation detection. When no conversation is detected, the volume is increased to maintain audio system effectiveness for music playback and entertainment. When conversation is detected, the volume is automatically reduced to improve conversation audibility. This dynamic adaptation ensures both audio system effectiveness and conversation clarity are maintained at different times.
Solution Approach 2:
The system uses continuous feedback from speech detection algorithms and acoustic environment monitoring to determine when to adjust volume. The feedback loop detects conversation states, speech patterns, and environmental noise levels, then adjusts volume accordingly to maintain both audio system effectiveness and conversation audibility in different operating conditions.
3Device complexity
If volume adjustment is based solely on vehicle speed, then road noise compensation is simplified, but conversation detection capability is lost
Solution Approach 1:
The system combines multiple functions into a unified volume control system: speed-based road noise compensation, conversation detection, speech pattern analysis, and dynamic volume adjustment. Instead of separate systems for each function, the patent integrates them to work together, using the same audio processing infrastructure for both road noise compensation and conversation detection.
Solution Approach 2:
The system uses feedback from speech detection and conversation state monitoring to supplement speed-based volume control. The feedback mechanism detects when conversations are occurring and adjusts volume accordingly, adding conversation-aware capability to the existing speed-based control system without requiring a completely separate control architecture.
4Measurement precision
If speech detection algorithms are made more complex to accurately identify conversations, then conversation detection accuracy improves, but processing requirements increase
Solution Approach 1:
The system applies speech detection and conversation analysis selectively rather than continuously at full complexity. Speech detection is performed to identify potential conversations, and more sophisticated analysis is applied only when speech is detected and conversation state is uncertain. This partial application of complex algorithms reduces overall processing requirements while maintaining accuracy when needed.
Solution Approach 2:
The speech and conversation detection process is segmented into multiple stages: initial speech detection, conversation state determination, Lombard effect detection, and fine-grained conversation analysis. Each stage processes only the necessary features for that specific detection task, dividing the complex processing into manageable segments that reduce overall computational requirements while maintaining detection accuracy.
Data Source
AI summary
Techniques are described for detecting a conversation between at least two people, and for reducing noise during the conversation. In certain embodiments, at least one speech metric is generated based on spectral analysis of an audio signal and is used to determine that the audio signal represents speech from a first person. Responsive to determining that the speech is part of a conversation between the first person and a second person an operating state of a device in a physical environment is adjusted such that a volume level of sound contributed by or associated with the device is reduced. The sound contributed by or associated with the device corresponds to noise, at least for the duration of the conversation. Therefore, reducing the volume level of sound contributed by or associated with the device reduces the overall noise level in the environment, resulting in a reduction in conversational effort.