The problem is as follows:
we have social media comments as text (e.g., "i love cheetos. but iPhone is great, too!")
We want a *module* that takes these comments (text) and demographic traits (age, gender) as input and outputs audio (speech) of a person speaking that text.
input: [text, age, gender] (e.g., "i love cheetos", 26, female)
output: audio file (i.e., speech)
sentiment: sad, happy, etc. => can the module be expanded to consider the sentiment of the comment in the tone of voice?
Deliverables: the module (i.e., script that takes the input and provides output as described above). In addition, a code notebook explaining the technical details of creating the module. The creation of the module needs to be replicable.
14 freelancers are bidding on average $675 for this job
Hi I have rich exp with text to speech(T2S) module. In the past, I used the module in unity and python. There are excellent speech services like google. So how do u think to cooperate with me? thanks Ivan.
I have many years of experience in using CNN for speech and text context analysis. Given the opportunity, I will deliver this project to your satisfaction.