Gender Model

The Gender model can classify speech into "male", "female", "unknown". The "unknown" class means that we cannot reliably classify the speech into "male" or "female". Because it only makes sense to apply this model to speech audio, it is combined with the SpeechRT model to increase the reliability of the results.

The receptive field of this model is 3130 milliseconds.

Specification

Receptive Field	Result Type
3130 ms	result ∈ ["female", "male", "unknown", "no_speech", "silence"]

Time-series

The time-series result will be an iterable with elements that contain the following information:

{
  "timestamp": 0,
  "results":{
    "gender": {
        "result": "female",  
        "confidence": 0.92
    }
  }
}

Time-series with raw values

If raw values were requested, they will be added to the time-series result:

{
  "timestamp": 0,
  "results":{
    "gender": {
        "result": "female",  
        "confidence": 0.92
    }
  },
  "raw": {
    "gender": {
      "male": 0.08,
      "female": 0.92
    }
  }
}

Summary

In case a summary is requested the following will be returned

{
  "gender": {
    "male_fraction": 0.30,
    "female_fraction": 0.60,
    "unknown_fraction": 0.05,
    "no_speech_fraction": 0.05,
    "silence_fraction": 0.0
  }
}

where x_fraction represents the percentage of time that x class was identified for the duration of the input.

Transitions

In case the transitions are requested a time-series with transition elements like shown below will be returned.

{
  "timestamp_start": 0,
  "timestamp_end": 1500,
  "result": "male",
  "confidence": 0.96
},
{
  "timestamp_start": 1500,
  "timestamp_end": 4000,
  "result": "female",
  "confidence": 0.89
}

The example above means that the first 1500ms of the audio snippet contained speech by male speaker(s), and between 1500ms and 4000ms female speaker(s) were detected.