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

Researchers reach human parity in conversational speech recognition

blogs.microsoft.com

Post reply on HN
Print view View original

111–120 of 164 posts

Re: Researchers reach human parity in conversational speech recognition

#111

Post by gingerrr »

Retric wrote: post #108
gingerrr wrote: post #107

Earlier quoted context omitted.

Your last example of the hyperintelligent space heater is exactly my point - the Turing test is a test of the (necessary) precondition of communication, but NOT a sufficient test of intelligence. In your example, the black box AI is assumed to be intelligent, but would still fail the Turing test - because intelligence is not a necessary condition for passing. Communicability IS necessary for the test. A passing grade…

Nothing you just said invalidates the test. X is a demonstration of intelligence says nothing about not X. If you can design something that passes an arbitrary touring tests yes it is intelligent. For example I could teach it any subject that works in text format. It could then pass an open ended essay test. And get a reasonable essay. Now, you could do the same thing with a pig and it would fail the test despite bei…

So help me, I think you've convinced me. I don't know what to do with all this leftover xkcd/386 though.

Thanks for the great chat.

Re: Researchers reach human parity in conversational speech recognition

#112

Post by healthnutter »

ralusek wrote: post #44
PravlageTiem wrote: post #30

Earlier quoted context omitted.

Being made to believe in a god isn't the same as believing in one. Silicon Valley thinks AI is not an epistemological problem, as if neurons can be perfectly simulated atomically and that all intelligence processes can be categorized as structured vs. unstructured. Very naive conclusions. Ironically, they BELIEVE if you simulate the axiomatic neuron perfectly, emergent properties of intelligence will mystically emerg…

For Artificial Intelligence to believe in God would be for it to believe in its makers, which are human. A machine would be intelligent to be aware that it was made by man. A man doesn't need to believe in God to be intelligent. In fact, the two are pretty much inversely related.

> A man doesn't need to believe in God to be intelligent. In fact, the two are pretty much inversely related.

Claiming as fact. Citation, please?

Re: Researchers reach human parity in conversational speech recognition

#113

Post by codekansas »

joe_the_user wrote: post #59
Eridrus wrote: post #3

The actual paper has a section on error analysis that is particularly enlightening: https://arxiv.org/abs/1610.05256 On the CallHome dataset humans confuse words 4.1% of the time, but delete 6.5% of words, most commonly deleting the word "I". Their ASR system confuses 6.5% of words on this dataset, but only deletes 3.3% of words, so depending on how you view this their claim about being better than humans isn't defin…

I was recently at a bar where they showed a movie with incomprehensible subtitles (English to English). I assume this was because they skimped and bought automatic subtitling. I think one important aspect is while humans miss words, they often get the sentence meaning correct. When computers miss words, they tend to substitute words that sound similar. That's readable if you have time but not necessarily as a stream…

From an ML perspective, recently there's been a lot more work done on language modeling (e.g. billion word corpus). Good language models can usually fix those types of perspective. So hopefully you can expect to see that change in the future!

Re: Researchers reach human parity in conversational speech recognition

#115

Post by braindead_in »

skoocda wrote: post #85
dfgonzalez wrote: post #77

Did someone put it as SaaS already?

We're close to an alpha release of Spreza, which might be relevant to your question. Look us up! dm me if you've got questions

Very cool. How do you compare to speechmatics?

Re: Researchers reach human parity in conversational speech recognition

#116

Post by aswanson »

joe_the_user wrote: post #59
Eridrus wrote: post #3

The actual paper has a section on error analysis that is particularly enlightening: https://arxiv.org/abs/1610.05256 On the CallHome dataset humans confuse words 4.1% of the time, but delete 6.5% of words, most commonly deleting the word "I". Their ASR system confuses 6.5% of words on this dataset, but only deletes 3.3% of words, so depending on how you view this their claim about being better than humans isn't defin…

I was recently at a bar where they showed a movie with incomprehensible subtitles (English to English). I assume this was because they skimped and bought automatic subtitling. I think one important aspect is while humans miss words, they often get the sentence meaning correct. When computers miss words, they tend to substitute words that sound similar. That's readable if you have time but not necessarily as a stream…

Hilarious that the grandparent states performance gained by deleting "I"from the training corpus and the child comment starts with that pronoun.

Re: Researchers reach human parity in conversational speech recognition

#117

Post by Arkaad »

ChrisClark wrote: post #83
joe_the_user wrote: post #59

Earlier quoted context omitted.

I was recently at a bar where they showed a movie with incomprehensible subtitles (English to English). I assume this was because they skimped and bought automatic subtitling. I think one important aspect is while humans miss words, they often get the sentence meaning correct. When computers miss words, they tend to substitute words that sound similar. That's readable if you have time but not necessarily as a stream…

It might have also been a 'bootleg' DVD from China or downloaded a version from there. I've had quite a few where they had done a horrible job translating into Chinese for the subtitles already, and then did a literal machine translation back to English. The character on the screen said "Hello", the English subtitle said "You good." Which would be the literal translation of nihao.

see also the infamous Star Wars Episode 3 Chinese bootleg "Do no want".

Re: Researchers reach human parity in conversational speech recognition

#118

Post by nercht12 »

gremlinsinc wrote: post #38
ghurtado wrote: post #29

Earlier quoted context omitted.

> I don't get why that's frustrating, without image and speech recognition AI isn't possible Wait, what? The most commonly known (and perhaps oldest) AI test in no way requires either image nor speech recognition. Millions of blind and deaf human beings would like to disagree with your claim that they are not intelligent or sentient beings. Seriously, what is the basis of this claim?

I'm not saying one can't be smart/intelligent without being able to see/hear, I'm saying if you take away all senses from ALL human beings there won't be any way to communicate at all, or know that others exist, and to learn from them. Learning is what makes intelligence possible--and the passing of information through generations. Hellen Keller fought extremely hard to overcome her sensory issues, but she had a good…

> Learning is what makes intelligence possible

Intelligence (at least in this case) is being able to take data and draw conclusions from it, but you just can't see such potential when you don't have input. Is a computer not a calculator when there's no software installed? No. It's still a calculator, but it just doesn't have inputs. One day, we may be able to give sight to the blind, but for now, considering such people without ANY learning capacity as "unintelligent" is still wrong.

Re: Researchers reach human parity in conversational speech recognition

#119

Post by ArkyBeagle »

saidajigumi wrote: post #80
radarsat1 wrote: post #35

The term "human parity" refers to a comparison of the error rate, which is a single scalar summarizing performance in terms of mistakes made. It says nothing about the kind of mistakes, and I can easily imagine that machines qualitatively do not make at all the same kind of mistakes as humans. I'd be curious to know if the kind of mistakes machines make might strike human listeners as quite stupid, but maybe not.. ma…

In my mind, this is analogous to the reasons why evaluation of lossy audio compression codecs requires human listening tests. Simply running some simplistic signal analysis like SNR (Signal-to-Noise Ratio) completely fails to capture the as-perceived quality of a compression implementation. To explore that analogy: In the case of lossy audio compression, the compressor deliberately introduces quantization noise into…

I've always evaluated audio codecs on differential signals - subtract A from A'. For telephony codecs, there are formal tests for MOS and/or PESQ .

Re: Researchers reach human parity in conversational speech recognition

#120

Post by ArkyBeagle »

PravlageTiem wrote: post #20
Lxr wrote: post #6

Earlier quoted context omitted.

I'm curious, what is your definition of AI?

A machine process qualifies as AI if it believes in a god. EDIT: I see the nuances of epistemological problems are lost to HN and knee-jerk culture war atheism still rules supreme.

On Westworld, one of the hosts referred to its creator in the presence of the character Robert Ford. Ford declined to identify himself as that person. Rather a nice riff, I thought.
Post reply on HN