Speech Recognition Is Not Solved • Hacker News Board

Re: Speech Recognition Is Not Solved

#41

Post by bagacrap » Tue, Oct 24, 2017, 5:55 PM UTC

twothamendment wrote: post #12

It is one thing to hear and correctly identify the words. It is another to understand the meaning. I've been thinking about this because my son has Auditory Processing Disorder, APD. He can hear great, even a whisper across the house. The trouble is the words don't always make sense. He can tell me the words he heard and they are correct, but assigning a meaning to them doesn't work like it does for most people. Afte…

> Since then I've thought about voice recognition differently. The AI to understand the context or fill in the blanks is what will make or break it.

Of course, and all humans rely on this as well. No one hears every word perfectly all the time --- it's impossible, because the source person doesn't pronounce every word perfectly all the time. Context clues are a huge part of speech recognition, as well as gestural typing recognition and other forms of machine interpretation of human input. While it's always been a component of NLP, you can clearly see it in action with the Android keyboard these days because after you type two words in a row, the first may be corrected after you enter the second one, based on context provided by the second one.

Re: Speech Recognition Is Not Solved

#42

Post by theresistor » Tue, Oct 24, 2017, 5:55 PM UTC

rav wrote: post #35

theresistor wrote: post #18

Speech recognition for multi-lingual speakers is another pain point. I live with a native French speaker, so my conversations naturally include a lot of French proper names, as well sometimes switching languages mid conversation or even mid sentence. Lots of recognition engines can handle English and French, but treat them as mutually exclusive. It frustrates me to no end when I know that Siri can recognize a French…

As a multi-lingual speaker I've even had problems with speech synthesis . For instance, Google Maps insists on narrating driving directions in the system language, which is set to English; this makes the narrated local non-English place names incomprehensible. If I succumb and change the system language I can understand the narrated place names, but in return I have to put up with the poor speech synthesis of non-Eng…

I was just in France last week suffering through the same problem. I’m American, so I want to keep my system set to English both due to familiarity of the interface and because I want data in familiar units (miles, degrees Fahrenheit), but it kills me when every street and place name is absolutely butchered.

Re: Speech Recognition Is Not Solved

#43

Post by fillskills » Tue, Oct 24, 2017, 5:58 PM UTC

noir_lord wrote: post #30

twothamendment wrote: post #12

It is one thing to hear and correctly identify the words. It is another to understand the meaning. I've been thinking about this because my son has Auditory Processing Disorder, APD. He can hear great, even a whisper across the house. The trouble is the words don't always make sense. He can tell me the words he heard and they are correct, but assigning a meaning to them doesn't work like it does for most people. Afte…

I'd never heard of APD. Interesting, all my life I've struggled to follow a conversation in a crowded environment, so much so that I actively avoid background noise with words in, I work with silicon ear plugs in or headphones and music with no lyrics. Looking at NHS symptoms they describe me as a child, didn't learn to read until I was 8. I nearly ended up in the remedial track but for a single awesome teacher who s…

Wow, I wish there was an easy way to pay back star teachers or mentors.

Re: Speech Recognition Is Not Solved

#44

Post by throwmenow_0140 » Tue, Oct 24, 2017, 5:58 PM UTC

cscurmudgeon wrote: post #3

Just the other day I was arguing (pleasantly) with someone here on HN saying that AI has solved speech rec (among other tasks). https://news.ycombinator.com/item?id=15429287 Wish this article was written a few days earlier. An analogue of this article exists for most other domains claimed to have been solved.

Sorry to bother you, but the translation of your comment is pretty good (English -> Spanish -> French -> English):

  No, it's not learning new classes of objects from a single image or a few images is very difficult. See
  http://www.sciencemag.org/content/350/6266/1332.short
  The machine translation is a joke.
  Put comments on this page by translating Google into another language and go back to English and see what you get.
  I did a little part of you. Just human level for just a simple little prayer.
  > But even if you do not make this assumption, identifying the object involves spitting the distance from the performance of the human level.

source: https://news.ycombinator.com/item?id=15429862

Not to debunk your claims, just interesting to see how good translation works (even if it's not human-level, I can understand what you say).

Re: Speech Recognition Is Not Solved

#45

Post by baddox » Tue, Oct 24, 2017, 5:59 PM UTC

dmreedy wrote: post #37

Of course it's not solved. We don't even know how to define the problem. Speech is[1] a fundamental component of Language, which is a fundamental component of Intelligence[2]. This is addressed somewhat in the conversation around semantic error rate; that there is more to processing raw audio speech than the calculus of mapping signals to tokens; some understanding of semantics and context is required to differentiat…

Problem definition really is the issue. Even appealing to the Turing test is less than satisfying. I’m fairly sure I’m a human, but Siri and similar will likely outperform me in certain categories like place names and popular music.

Re: Speech Recognition Is Not Solved

#46

Post by theresistor » Tue, Oct 24, 2017, 5:59 PM UTC

theresistor wrote: post #42

rav wrote: post #35

Earlier quoted context omitted.

As a multi-lingual speaker I've even had problems with speech synthesis . For instance, Google Maps insists on narrating driving directions in the system language, which is set to English; this makes the narrated local non-English place names incomprehensible. If I succumb and change the system language I can understand the narrated place names, but in return I have to put up with the poor speech synthesis of non-Eng…

I was just in France last week suffering through the same problem. I’m American, so I want to keep my system set to English both due to familiarity of the interface and because I want data in familiar units (miles, degrees Fahrenheit), but it kills me when every street and place name is absolutely butchered.

An interesting observation I made last week was that the poor synthesis of French street names in English mode was worse than American-mispronouncing-French level. I wonder if that exposes some level of mismatch between how the synthesis engine models language and how humans do.

Re: Speech Recognition Is Not Solved

#47

Post by themihai » Tue, Oct 24, 2017, 5:59 PM UTC

ddevault wrote: post #8

johnramsden wrote: post #6

What I would like to see you would be an open source speech recognition system that is easy to use, and works. There is really no match for the proprietary solutions in the open source world right now, and that is disappointing. Not to say that there aren't open source speech recognition systems, they just aren't completely usable in the way proprietary solutions are. A lot of research goes into open source speech re…

I agree - I don't care how good Google gets it, this is an unsolved problem until I can do it with open source tools operating without an internet connection.

I don't think "donate your voice" will ever work. They should incorporate it in a product and add a checkbox to share your voice/statistics to improve the system.

Re: Speech Recognition Is Not Solved

#48

Post by ccozan » Tue, Oct 24, 2017, 6:00 PM UTC

Speech Recognition, beside transcribing phonemes and match to a NN of possible words, is not solved because speech is highly integrated with the human context: who is speaking, to whom is speaking, where is the speech happening, why is the speech initiated, and so on.

My kids needed 5-6 years of continous daily talking until I could say they understand a conversation almost completly. Every single word or phrase I directed at them was spoken in a certain context and had a certain role in communicating with them when from the context it wasn't clear what my intentions were. Of course, they had their fun, throwing words away and repeating endlesly some funny word or phrase or terribly spelling them. It is interesting that you as an adult need too learn their own prononciation, at some moment in time I even wrote a small dictionary.

Again, speech recognition will simply stay at recognizing phonemes/words only for a very long time, until we have a true AI Assistant that walks with us, sees with us, and hears with us in the same time. Then it can apply some semantic and other context based related NN.

Re: Speech Recognition Is Not Solved

#49

Post by awnihannun » Tue, Oct 24, 2017, 6:02 PM UTC

aidenn0 wrote: post #23

I think some people overestimate how good humans are at speech recognition. Unfamiliar accents and noisy environments cause havoc with many people. I had a friend who learned English in India when I was in High School, so I was used to that accent; many of my classmates in College could not understand anything our Indian T/A said freshmen year. Similarly I had friends for whom English was a second language who had li…

I agree with your point. It can be hard for a US native English speaker to recognize a Scottish accent.

But, other Scottish people certainly don't have trouble with understanding a Scottish accent. So I view that as a certificate that we should be able to build a speech recognizer which can recognize Scottish accents.

Re: Speech Recognition Is Not Solved

#50

Post by backpropaganda » Tue, Oct 24, 2017, 6:03 PM UTC

dsacco wrote: post #16

johnramsden wrote: post #6

What I would like to see you would be an open source speech recognition system that is easy to use, and works. There is really no match for the proprietary solutions in the open source world right now, and that is disappointing. Not to say that there aren't open source speech recognition systems, they just aren't completely usable in the way proprietary solutions are. A lot of research goes into open source speech re…

Is it an issue of open source software being inadequate, or is it the lack of sufficient training data and compute power local to your home? I’m under the impression that Google is mostly dogfooding its open source tooling for machine learning in GCP, and actually differentiates based on trained models and compute power.

A bit of both. When data doesn't exist, people aren't motivated enough to create the open source tools which would leverage it. While Librispeech is okay for academic research, it's not enough to create a good production-grade speech recognition system.