PhonMatchNet icon indicating copy to clipboard operation
PhonMatchNet copied to clipboard

verified publisher icon ncsoft
→

Metadata

Official implementation of "PhonMatchNet: Phoneme-Guided Zero-Shot Keyword Spotting for User-Defined Keywords" (INTERSPEECH 2023)

Results 4 PhonMatchNet issues
Sort by recently updated
recently updated
newest added

Generate training data code

Hello! Thank you very much for your work! I am currently facing some issues.“Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting” this paper mentioned that the training set involves approximately 8000k...

GabrielHaoHao avatar GabrielHaoHao

about training set

1 comment

Hello! Thank you very much for your work! I am currently facing some issues. The training set I made according to the original paper never meets the number of 8000k...

GabrielHaoHao avatar GabrielHaoHao

Train with self training data

Would it be possible to train the model with my training data? If so, due to dockerization, is unclear what should it be the data preprocessing to do so. I...

Alexi2Cat avatar Alexi2Cat

ImportError: cannot import 'libriphrase'

Hi, I'm now facing an issue and can't find out what went wrong. When I tried to run the script "train.py" it just showed me the error message: File ".\train.py",...

ORALOG avatar ORALOG

← Metadata

23
Stars
6
Forks
Watchers

Owner

verified publisher icon ncsoft

Metadata

Official implementation of "PhonMatchNet: Phoneme-Guided Zero-Shot Keyword Spotting for User-Defined Keywords" (INTERSPEECH 2023)

Back