Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition

github.com

Post reply on HN
Print view View original

11–20 of 43 posts

Re: Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition

#11

Post by braindead_in »

bmc7505 wrote: post #6

A few weeks ago, a deep learning researcher at one of the world's leading speech groups told me off-the-record that offline, human-parity speech recognition would be "coming soon" to mobile devices. Not sure s/he realized just how soon that would be. Even though state-of-the-art ASR is really expensive to train, recognition is extremely cheap to run, even on lower-power devices. [1][2] With specialized silicon, you c…

A consumer focused human parity ASR service will disrupt so many industries, including mine. I run a human powered transcription service where we transcribe files with high accuracy. I am just waiting for the day when our transcribers can work off a auto-generated transcript instead of typing it all up manually. I'll pay good money for a service where I can just send a file and get a 80-90% accurate transcript with speaker diarization.

Re: Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition

#12

Post by echelon »

Did the original WaveNet text to speech demo come with a paper or source code? (I didn't see either.) I'm interested in techniques, particularly neural network-related, to improve the quality of my Donald Trump text to speech engine [1].

Does anyone on HN do active research in this field? Could I pick your brain for a survey of the best papers (especially review papers) on the subject?

[1] http://jungle.horse

Re: Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition

#13

Post by doublerebel »

throwaway13337 wrote: post #4

This seems super useful for most speech recognition - understanding context. It doesn't seem like the mainstream engines (Alexa, Google Voice, Siri) are context aware. Why not?

Context involves location, which 99% of the time those bots don't take into consideration. Context does not involve knowing everything about your email or being able to search the entire web. It's much more connected to what you just did and where and when you are doing it.

This is what I'm solving at Optik. Helping you manage the things that you care about in the place that you are, and NOT exposing your personal details to cloud computation.

Re: Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition

#14

Post by imaginenore »

braindead_in wrote: post #11
bmc7505 wrote: post #6

A few weeks ago, a deep learning researcher at one of the world's leading speech groups told me off-the-record that offline, human-parity speech recognition would be "coming soon" to mobile devices. Not sure s/he realized just how soon that would be. Even though state-of-the-art ASR is really expensive to train, recognition is extremely cheap to run, even on lower-power devices. [1][2] With specialized silicon, you c…

A consumer focused human parity ASR service will disrupt so many industries, including mine. I run a human powered transcription service where we transcribe files with high accuracy. I am just waiting for the day when our transcribers can work off a auto-generated transcript instead of typing it all up manually. I'll pay good money for a service where I can just send a file and get a 80-90% accurate transcript with s…

I hope you realize your business is about to go out of business. The only reason you can charge people now is because the automatic recognition sucks compared to humans.

Re: Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition

#15

Post by craigbaker »

Is this really speech recognition from raw waveforms? It looks like they're extracting MFCC features from the raw audio, and using that as input to the neural network. I thought that the point of WaveNet was that it took the raw waveform directly as input, unlike previous architectures which first extract spectral features such as MFCCs to use as the input.

Re: Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition

#16

Post by gambler »

"Some of Deepmind's recent papers are tricky to reproduce. The Paper also omitted specific details about the implementation, and we had to fill the gaps in our own way."

So, I'm not the only one seeing this issue. It seems like many recent AI papers want to look as impressive as possible, wile giving you as little implementation info as possible. This bothers me, because it opposes the very purpose of research publication.

Re: Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition

#17

Post by braindead_in »

imaginenore wrote: post #14
braindead_in wrote: post #11

Earlier quoted context omitted.

A consumer focused human parity ASR service will disrupt so many industries, including mine. I run a human powered transcription service where we transcribe files with high accuracy. I am just waiting for the day when our transcribers can work off a auto-generated transcript instead of typing it all up manually. I'll pay good money for a service where I can just send a file and get a 80-90% accurate transcript with s…

I hope you realize your business is about to go out of business. The only reason you can charge people now is because the automatic recognition sucks compared to humans.

We do super-human-parity transcripts. Our transcripts are insanely accurate, even for challenging files. I'm sure computers will be able to do that one day, but Singularity would have already happened by then, wiping out many businesses. I for one look forward to Singularity and hope that we will contribute to it in some way.

Re: Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition

#18

Post by bertiewhykovich »

braindead_in wrote: post #17
imaginenore wrote: post #14

Earlier quoted context omitted.

I hope you realize your business is about to go out of business. The only reason you can charge people now is because the automatic recognition sucks compared to humans.

We do super-human-parity transcripts. Our transcripts are insanely accurate, even for challenging files. I'm sure computers will be able to do that one day, but Singularity would have already happened by then, wiping out many businesses. I for one look forward to Singularity and hope that we will contribute to it in some way.

I'm rooting against you, pal. Cheers.

Re: Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition

#19

Post by imaginenore »

braindead_in wrote: post #17
imaginenore wrote: post #14

Earlier quoted context omitted.

I hope you realize your business is about to go out of business. The only reason you can charge people now is because the automatic recognition sucks compared to humans.

We do super-human-parity transcripts. Our transcripts are insanely accurate, even for challenging files. I'm sure computers will be able to do that one day, but Singularity would have already happened by then, wiping out many businesses. I for one look forward to Singularity and hope that we will contribute to it in some way.

What's super-human parity? And how do you achieve it using humans?

Re: Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition

#20

Post by RandomInteger4 »

How much Bandwidth is consumed from voice communications such as when speaking to someone on Skype or over the phone, vs. the same words transmitted via text?

Perhaps future communication applications can have a WaveNet on either end, which learns the voice of the person you're communicating with and then only sends text after a certain point in the conversation?

I'm coming at this from a point of ignorance though, so correct me if I've made erroneous assumptions.

Post reply on HN