gid-gb-v2 (Gender Identification)
Version Changelog
| Plugin Version | Change |
|---|---|
| v2.0.0 | Initial plugin release, functionally identical to v1.0.0, but updated to be compatible with OLIVE 5.0.0 |
| v2.0.1 (latest) | Updated to be compatible with OLIVE 5.1.0+, released with 5.2.0 |
Description
Gender Identification (GID) plugins attempt to identify the gender of the talker in the audio submitted to the plugin for scoring. The goal is to distinguish between male and female speakers as a quick triage of incoming data, or to serve as a front-end for other plugins that may have a gender-specific workflow.
This plugin is powered by a Gaussian backend.
Domains
- clean-v1
- Generic domain for most close talking conditions with signal-to-noise ratio above 10 dB.
Inputs
Audio file or buffer and an optional identifier.
Outputs
Gender ID plugins report a score for each gender, in the format shown below. The plugins created so far feature score scaling, meaning that the scores returned for male and female are re-scaled so that their values sum to 1.0, in order to facilitate legibility.
input-audio.wav f 0.1
input-audio.wav m 0.9
Functionality (Traits)
The functions of this plugin are defined by its Traits and implemented API messages. A list of these Traits is below, along with the corresponding API messages for each. Click the message name below to go to additional implementation details below.
- GLOBAL_SCORER – Score all submitted audio, returning a single score for the entire audio segment for each gender.
Compatibility
OLIVE 5.2+
Limitations
Labeling Granularity
GID plugins assume that an audio segment contains only a single gender and may be scored as a unit. If a segment contains multiple speakers who may or may not be of a different gender, the entire segment will still be scored as a unit. Ensuring that audio submitted for scoring consists of a single speaker is important for reliable results.
Age
All current Gender ID plugins are trained only on adult male and female speech. Speech from children will likely be confused with female speech, or be otherwise volatile.
Interface
For command line interface use see the appropriate section of the OLIVE CLI User Guide. For API usage see the appropriate section of the OLIVE Application Programming Interface Guide.