HAAQI Speech Intelligibility model
This is a python implementation of the Hearing Aid Audio Quality Index (HAAQI) model which is used for objective estimation. This will be used in the stage 1 evaluation of entrants (see Rules).
Note that HAAQI is not a binaural metric, instead, each channel must be processed separately. We average the left and right scores to produce a final overall score.
You can call the HAAQI metric using the
clarity.evaluator.haaqi.compute_haaqi function as:
processed_signalcorresponds to the output signal from
enhancementblock in the baseline.
reference_signalcorresponds to the amplified reference signal. This is generated by the
evaluationblock in the baseline.
- It is recommended to resample the
reference_signalsignals to 24,000 Hz before calling the metric.
- Set the parameters
- The audiogram corresponds to the left or right
equalisationto 2, which indicates to HAAQI that the
NAL-Rapplied to it.
- Set the
level1parameter to the level of the reference signal before applying the hearing aid amplification (NAL-R). Recommended to set it as
65 - 20 * log10(RMS(reference signal before NAL-R))
Please note that the
level1 parameter uses the reference signal without NAL-R amplification.
reference_signal expects the amplified version of the same signal used in
 Byrne, Denis, and Harvey Dillon. "The National Acoustic Laboratories'(NAL) new procedure for selecting the gain and frequency response of a hearing aid." Ear and hearing 7.4 (1986): 257-265.