does anyone know of good ways to do the opposite, speech to text?
Lex by AWS.
Its the same deep learning tech. used as used by Alexa
Deep Voice: Real-Time Neural Text-To-Speech
11–20 of 80 posts
Re: Deep Voice: Real-Time Neural Text-To-Speech
#12Interesting. They are not TTS like we are accustomed to, they are replicating a specific persons voice with TTS. Listen to the ground-truth recordings at the bottom and then the synthesized versions above. "Fake News" is about to get a lot more compelling when you can make anyone say anything as long as you have some previous recordings of their voice.
> you can make anyone say anything as long as you have some previous recordings of their voice. That's not what this is doing. They're simply resynthesizing exactly what the person said, in the same voice. It's essentially cheating because they can use the real person's inflection. Generating correct inflection is the hardest part of speech synthesis because doing it perfectly requires a complete understanding of the…
>The top two are representative of what it sounds like when doing true text to speech. The middle five are just resynthesis of a clip saying the exact same thing.
Gotcha, now I understand.
Re: Deep Voice: Real-Time Neural Text-To-Speech
#13Re: Deep Voice: Real-Time Neural Text-To-Speech
#14does anyone know of good ways to do the opposite, speech to text?
Depends on how good you're talking. Chrome supports the SpeechRecognition API. https://developer.mozilla.org/en-US/docs/Web/API/SpeechRecog...
i'm more thinking of ways to programmatically turn long audio files into indexable text.
Re: Deep Voice: Real-Time Neural Text-To-Speech
#15Earlier quoted context omitted.
Depends on how good you're talking. Chrome supports the SpeechRecognition API. https://developer.mozilla.org/en-US/docs/Web/API/SpeechRecog...
i'm more thinking of ways to programmatically turn long audio files into indexable text.
I'm unaware of a ML-based solution, but GCE has an endpoint that _can_ do this, though it is better at short sentences.
Re: Deep Voice: Real-Time Neural Text-To-Speech
#16Hey there! I'm one of the authors of the paper and I'm happy to answer any questions anyone may have!
Make sure to check out the paper on arxiv as well.
Re: Deep Voice: Real-Time Neural Text-To-Speech
#17Hey there! I'm one of the authors of the paper and I'm happy to answer any questions anyone may have! Make sure to check out the paper on arxiv as well.
Nice job! The samples sound good.
Is there an implementation of this to check out? It seems like you needed to write some custom, low-level code to implement this in real-time. Which libraries did you use to generate the ANNs and do the inferences?
Re: Deep Voice: Real-Time Neural Text-To-Speech
#18Hey there! I'm one of the authors of the paper and I'm happy to answer any questions anyone may have! Make sure to check out the paper on arxiv as well.
Nice job! The samples sound good. Is there an implementation of this to check out? It seems like you needed to write some custom, low-level code to implement this in real-time. Which libraries did you use to generate the ANNs and do the inferences?
We are not currently releasing any code, but hopefully the paper on arxiv is enough to make it easy to reproduce the result.
We use TensorFlow for writing and training the model and c++ with a lot of hand optimizations for inference, with assembly kernels written with PeachPy (which is an awesome piece of software!)
Re: Deep Voice: Real-Time Neural Text-To-Speech
#19OK, that went from uncanny valley to flipping amazing. I could picture the person speaking. An old lady. A young woman. It was hard to picture an algorithm in a machine. It's amazing that is all boils down to 1s and 0s and some boolean logic.
You've misunderstood what you're listening to, I suggest reading the post again.
The recordings at the bottom are just recordings of an old lady and a young woman.
Re: Deep Voice: Real-Time Neural Text-To-Speech
#20Earlier quoted context omitted.
Nice job! The samples sound good. Is there an implementation of this to check out? It seems like you needed to write some custom, low-level code to implement this in real-time. Which libraries did you use to generate the ANNs and do the inferences?
We are not currently releasing any code, but hopefully the paper on arxiv is enough to make it easy to reproduce the result. We use TensorFlow for writing and training the model and c++ with a lot of hand optimizations for inference, with assembly kernels written with PeachPy (which is an awesome piece of software!)
I didn't know Baidu uses TensorFlow! Is that the main framework there now or are others in use?