Abstract: An audio processing system has multiple microphones that capture an audio signal. A noise suppression circuit analyses the audio signal to detect a type of noise present in the signal (e.g., stationary or non-stationary background noise). Based on the detected background noise type, the system operates in either a first or second mode of operation. In the first mode (stationary noise detected), one microphone is used to enhance a speech signal from the audio signal, and in the second mode (non-stationary noise detected), more than one microphone is used to enhance the speech signal. Processing more than one microphone input signal requires additional complexity and more processing power than one-microphone speech enhancement, so by classifying the background noise type and then switching between one microphone or N-microphones based speech enhancement, processing power is reduced during stationary noise conditions.

Abstract: A mechanism to adjust far-end signal loudness based on environmental noise levels and device speaker characteristics has a noise-level analyzer that receives feedback from an intelligent speaker-boosting logic circuit that provides a signal to a class-D amplifier to drive the speaker. The noise-level analyzer analyzes near-end environmental noise levels and far-end speech input signal levels across critical frequency bands. The noise-level analyzer performs a masking analysis of the far-end and near-end signals, and guides the speaker-boosting logic circuit to apply determined signal boosting levels over selective bands. The speaker-boosting logic circuit monitors system activity along with the selective band boosting guidance from the noise-level analyzer. Using device speaker information and the speaker excursion pattern, the speaker-boosting logic circuit adjusts far-end speech signal loudness without over excursion of the speaker and damage to the speaker hardware.

Abstract: A mechanism to adjust far-end signal loudness based on environmental noise levels and device speaker characteristics has a noise-level analyzer that receives feedback from an intelligent speaker-boosting logic circuit that provides a signal to a class-D amplifier to drive the speaker. The noise-level analyzer analyzes near-end environmental noise levels and far-end speech input signal levels across critical frequency bands. The noise-level analyzer performs a masking analysis of the far-end and near-end signals, and guides the speaker-boosting logic circuit to apply determined signal boosting levels over selective bands. The speaker-boosting logic circuit monitors system activity along with the selective band boosting guidance from the noise-level analyzer. Using device speaker information and the speaker excursion pattern, the speaker-boosting logic circuit adjusts far-end speech signal loudness without over excursion of the speaker and damage to the speaker hardware.

Abstract: An audio processing system has multiple microphones that capture an audio signal. A noise suppression circuit analyses the audio signal to detect a type of noise present in the signal (e.g., stationary or non-stationary background noise). Based on the detected background noise type, the system operates in either a first or second mode of operation. In the first mode (stationary noise detected), one microphone is used to enhance a speech signal from the audio signal, and in the second mode (non-stationary noise detected), more than one microphone is used to enhance the speech signal. Processing more than one microphone input signal requires additional complexity and more processing power than one-microphone speech enhancement, so by classifying the background noise type and then switching between one microphone or N-microphones based speech enhancement, processing power is reduced during stationary noise conditions.