Wow train.py contains only 83 lines of code (including a few empty lines and commets). And recognize.py is only litte bit longer with 108 lines. Very impressive.
typical of machine learning, a whole lot of talking about a few lines of code
Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition
21–30 of 43 posts
Re: Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition
#22"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 public…
Unfortunately I think you'll find similar complaints in every scientific field. Often, results either aren't described well enough to be reproduced, they're too expensive or difficult to reproduce, or they rely on closed-source software and/or inadequately-documented hardware.
Re: Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition
#23Earlier quoted context omitted.
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?
Presumably more accurate than a single human, and you can do it with multiple humans and reaching a consensus. I remember an anecdote in physics class where an experiment required counting a certain number of events in time. A single person would occasionally blink and miss an event. But if you had two people, and you count how many people observed each event, you can solve for super-human accuracy using the estimated error rates of each person.
See also this usage in the context of ML:
Re: Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition
#24"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 public…
This is more specific to deepmind actually, Facebook and others have been pretty good about publishing code.
Re: Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition
#25How 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, s…
text communication is much lighter (a few bytes/s vs kb/s) but you may miss the non verbal contents of voice
Re: Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition
#26This is really exciting. I previously worked at a startup for that could have benefited enormously from even 90% accurate speech recognition. As of six months ago when I last looked, there were no open source speech-to-text libraries with anything approaching the performance of the proprietary work by Google, Microsoft, Baidu, etc. The closest thing was CMU Sphinx, but its accuracy was unacceptable.
Props to the author, and especially to the DeepMind researchers who published their work! I look forward to living in a world where this type of technology is ubiquitous and mostly commoditized.
Re: Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition
#27A 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…
We've chatted - just an update that I'm implementing diarization this weekend :)
Re: Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition
#28This is really exciting. I previously worked at a startup for that could have benefited enormously from even 90% accurate speech recognition. As of six months ago when I last looked, there were no open source speech-to-text libraries with anything approaching the performance of the proprietary work by Google, Microsoft, Baidu, etc. The closest thing was CMU Sphinx, but its accuracy was unacceptable. Props to the auth…
The CMU Sphinx project as it stands is basically dead. Even though they recently implemented some sequence-to-sequence deep learning techniques for g2p [1], the core stack is still based on an ancient GMM/HMM pipeline, and current state of the art projects (even open source ones) have leapfrogged it in terms of accuracy. If you're implementing offline speech recognition today, start with something like this or Kaldi-ASR [2]. It will take a bit of work to get your models to running on a mobile device, but the end result will be much more usable.
[1] http://cmusphinx.sourceforge.net/2016/04/grapheme-to-phoneme...
Re: Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition
#29Is 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.
Apparently, they tried to use the raw audio waveform with the original setup from the WaveNet paper but couldn't get it to train on their TitanX, so they used MFCCs instead. It's not exactly clear why this is the case.
"Second, the Paper added a mean-pooling layer after the dilated convolution layer for down-sampling. We extracted MFCC from wav files and removed the final mean-pooling layer because the original setting was impossible to run on our TitanX GPU." [1]
[1] https://github.com/buriburisuri/speech-to-text-wavenet#speec...