KeenResearch.ASRAudioQualityResult Class Reference

Audio quality metrics computed during recognition. Provided as part of the response to help assess recording conditions (noise, clipping, signal level). More...

Public Attributes
int	clippedSampleCount
	Number of raw audio samples that were clipping (reaching min/max value). Clipping may indicate the user is too close to the microphone.
double	snrValue
	Estimated signal-to-noise ratio in dB (meanSpeechRmsValue - meanNonSpeechRmsValue). Low values will affect recognition performance. Zero if insufficient data.
double	meanSpeechRmsValue
	Mean frame RMS level for speech segments in dB. Zero if no speech detected.
double	meanNonSpeechRmsValue
	Mean frame RMS level for noise (non-speech) segments in dB.
double	peakSpeechRmsValue
	Estimated peak RMS level of speech in dB (98th percentile, filtering outliers). Low values indicate faint speech or user too far from mic. Zero if no speech detected.
bool	initialSegmentRmsWarning
	True if high RMS was detected during the initial audio segment, which may indicate device audio playback, late recognizer start, or high ambient noise.
double[]	frameRmsValues
	Per-frame RMS values in dB (25ms frames with 10ms shift). Computed as 20*log10(sqrt(sum of squared samples)). Approximately -100 dB for silent frames.

Detailed Description

Audio quality metrics computed during recognition. Provided as part of the response to help assess recording conditions (noise, clipping, signal level).

Member Data Documentation

clippedSampleCount

int KeenResearch.ASRAudioQualityResult.clippedSampleCount

Number of raw audio samples that were clipping (reaching min/max value). Clipping may indicate the user is too close to the microphone.

frameRmsValues

double [] KeenResearch.ASRAudioQualityResult.frameRmsValues

Per-frame RMS values in dB (25ms frames with 10ms shift). Computed as 20*log10(sqrt(sum of squared samples)). Approximately -100 dB for silent frames.

initialSegmentRmsWarning

bool KeenResearch.ASRAudioQualityResult.initialSegmentRmsWarning

True if high RMS was detected during the initial audio segment, which may indicate device audio playback, late recognizer start, or high ambient noise.

meanNonSpeechRmsValue

double KeenResearch.ASRAudioQualityResult.meanNonSpeechRmsValue

Mean frame RMS level for noise (non-speech) segments in dB.

meanSpeechRmsValue

double KeenResearch.ASRAudioQualityResult.meanSpeechRmsValue

Mean frame RMS level for speech segments in dB. Zero if no speech detected.

peakSpeechRmsValue

double KeenResearch.ASRAudioQualityResult.peakSpeechRmsValue

Estimated peak RMS level of speech in dB (98th percentile, filtering outliers). Low values indicate faint speech or user too far from mic. Zero if no speech detected.

snrValue

double KeenResearch.ASRAudioQualityResult.snrValue

Estimated signal-to-noise ratio in dB (meanSpeechRmsValue - meanNonSpeechRmsValue). Low values will affect recognition performance. Zero if insufficient data.