Super cool work, congrats BoldVoice team! I've always thought that one of the non-obvious applications of voice cloning/matching is the ability to show a language learner what they would sound like with a more native accent.
19 karma · joined March 24, 2011
Speak (YC W17) is an AI English tutor on your phone. Our app features a cast of fun virtual characters that we’ve carefully created to improve your English fluency as quickly as possible. We’re building speech recognition that can understand heavy accents and that lets users actually have conversations in English—without needing a human partner.
We launched only a few months ago and users all around the world are already having over 50,000 conversations per week with our virtual characters. We’re backed by Y Combinator and some of the best investors in the world.
We’re looking for our first iOS/Swift engineer to lead mobile development and eventually help grow and lead the team. We want to talk to you if you are a curious person, care about the details of a great user experience, and can build fast.
We’re currently a tiny team of 4 working out of a beautiful brick office in the SoMa district of San Francisco. Email us at jobs@usespeakeasy.com, and come help us build the way the next billion people will learn English.
Speak (YC W17) is an AI English tutor on your phone. Our app features a cast of fun virtual characters that we’ve carefully created to improve your English fluency as quickly as possible. We’re building speech recognition that can understand heavy accents and that lets users actually have conversations in English—without needing a human partner.
We launched only a few months ago and users all around the world are already having over 50,000 conversations per week with our virtual characters. We’re backed by Y Combinator and some of the best investors in the world.
We’re looking for our first iOS/Swift engineer to lead mobile development and eventually help grow and lead the team. We want to talk to you if you are a curious person, care about the details of a great user experience, and can build fast.
We’re currently a tiny team of 4 working out of a beautiful brick office in the SoMa district of San Francisco. Email us at jobs@usespeakeasy.com, and come help us build the way the next billion people will learn English.
Speak (YC W17) is an AI English tutor on your phone. Our app features a cast of fun virtual characters that we’ve carefully created to improve your English fluency as quickly as possible. We’re building speech recognition that can understand heavy accents and that lets users actually have conversations in English—without needing a human partner.
We launched only a few months ago and users all around the world are already having over 50,000 conversations per week with our virtual characters. We’re backed by Y Combinator and some of the best investors in the world.
We’re looking for our first iOS/Swift engineer to lead mobile development and eventually help grow and lead the team. We want to talk to you if you are a curious person, care about the details of a great user experience, and can build fast.
We’re currently a tiny team of 4 working out of a beautiful brick office in the SoMa district of San Francisco. Email us at jobs@usespeakeasy.com, and come help us build the way the next billion people will learn English.
Read the how to on reading data from files: https://www.tensorflow.org/versions/r0.8/how_tos/reading_dat...
and check out this useful Stack Overflow answer: http://stackoverflow.com/questions/33648322/tensorflow-image...
How does this work? What did you use as training data? Do you parse the sentence in any way?
For example, "Hey! It was so so great to see you." gets a 46/100, and 'so' is listed as an impolite word, which is understandable in some contexts but not this one.
I'd be really happy if I could consistently find a $5 meal in SF.