Models Overview

The DeepTone™ SDK comes with a set of different models. Each model is optimized to give insights on a certain voice property.

Example

E.g. the Gender model predicts the gender of voice in a given audio snippet.

Integrated speech-detector

Finding voice properties only works if there is a voice to classify in a given audio snippet. This is why all the models that give insights on voice are combined with our Speech model. The Speech model can categorize audio into three categories:

  • Speech
  • Music
  • No Speech

Currently we consider everything that is neither speech nor music to be 'No Speech', including silence. We will be able to categorize audio into a wider range of categories with our Silence detector and HumanSounds model (coming soon ...).

Model output

Each of our classifier models will return an iterable that contains a time-series of predictions. Each element of the time-series contains the following information:

  • Timestamp - in milliseconds
  • Confidence - float ∈ [0,1]
  • Model result - depends on the model that is used

Optionally a user can also request a summary and transitions components in addition to the time-series result when processing a file. More information about those can be found in the file-processing section.

Receptive field

Each model has a different receptive field - the minimum amount of data it needs to process before it produces reliable results. This means that if you request a model to process data it can output results as often as desired (minimum every 64ms and a multiple of it) but the initial results might not be accurate since there was not enough data to math the receptive field. Also note that if you request your data to be processed by multiple models at the same time, each might start producing accurate results at different points in time, depending on their receptive fields.

Output period

All models can output predictions at best at every 64ms of audio data.

Detailed information on how to configure the properties of a model can be found in the Usage section. The following models are currently included in the DeepTone™ SDK:

ModelDescriptionOutputReceptive Field
SpeechSpeech classifier that can detect music, general noise, or human speech.speech | no_speech | music1082ms
GenderSpeaker gender classifiermale | female | unknown | no_speech1851 ms
ArousalSpeaker arousal classifierlow | neutral | high | no_speech2107 ms