Hello,
We want to build application which search given keywords from broadcasts, news (radio, tv) in Mongolian language.
Is it good enough to train these keywords only?
We just want an answer for these keywords occurred in given recordings or didn't, if yes then which one and when?
Can CMU Sphinx help us on this?
Thank you
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
No, you need to use full-scale acoustic model. Though it could be trained on keywords mostly, it still needs to include significant portion of the other words of the language.
We just want an answer for these keywords occurred in given recordings or didn't, if yes then which one and when?
Can CMU Sphinx help us on this?
Yes, see pocketsphinx_kws tool.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hello,
We want to build application which search given keywords from broadcasts, news (radio, tv) in Mongolian language.
Is it good enough to train these keywords only?
We just want an answer for these keywords occurred in given recordings or didn't, if yes then which one and when?
Can CMU Sphinx help us on this?
Thank you
Hello
No, you need to use full-scale acoustic model. Though it could be trained on keywords mostly, it still needs to include significant portion of the other words of the language.
Yes, see pocketsphinx_kws tool.