Automatic Spoken Language Identification using a Time-Delay Neural Network. (arXiv:2205.09564v1 [cs.CL])

Closed-set spoken language identification is the task of recognizing the
language being spoken in a recorded audio clip from a set of known languages.
In this study, a language identification system was built and trained to
distinguish between Arabic, Spanish, French, and Turkish based on nothing more
than recorded speech. A pre-existing multilingual dataset was used to train a
series of acoustic models based on the Tedlium TDNN model to perform automatic
speech recognition. The system was provided with a …

arxiv identification language network neural network time