Hello all,
I hope you are doing great.
I am trying to use two modalities (audio and text) for a machine translation task.
I have built a parallel corpus and I have the monolingual audio for one of the languages that I am working on.
Unfortunately, I have some challenges working with audio and merging it with text.
I greatly appreciate any help here so that I can move forward with this project.
I am open to collaboration (e.g. scientific articles, etc.) with people who are interested in working with me.
If you are an expert in NLP (machine translation) or know how to work with multimodal deep learning domains, please do not hesitate to contact me.
my email: qandeasal1991@gmail.com
Thank you in advance for your time.
Cheers,
Soheila