This is an implementation of a baseline for low resource language intent classier model. The model recognizes a sequence of phonemes and output an intent. To emulate a low resource situation, the model is trained and evaluated on different combinations of speakers and utterances. Starting with one speaker and one utterance up to 7 speakers and 7 utterances. Basically the model is trained and evaluated on 49 different combinations.
-
Notifications
You must be signed in to change notification settings - Fork 0
This is an implementation of a baseline for low resource language intent classier model. The model recognizes a sequence of phonemes and output an intent. To emulate a low resource situation, the model is trained and evaluated on different combinations of speakers and utterances. Starting with one speaker and one utterance up to 7 speakers and 7…
enn72/Low-Resource-Intent-Classifier
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
This is an implementation of a baseline for low resource language intent classier model. The model recognizes a sequence of phonemes and output an intent. To emulate a low resource situation, the model is trained and evaluated on different combinations of speakers and utterances. Starting with one speaker and one utterance up to 7 speakers and 7…
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published