New services expand IBM Watson capabilities to images, speech, and more • Hacker News Board

Re: New services expand IBM Watson capabilities to images, speech, and more

#91

Post by jsstylos » Thu, Feb 05, 2015, 9:55 PM UTC

Caligula wrote: post #90

pesenti wrote: post #2

Some context on the new services. They are built on technology that comes from IBM Research and has been moved into the Watson group in 2014. Some like speech, have been developed for more than 50 years. None of these technologies have overlap with the Watson Jeopardy stack (except for the Watson voice). We will release that stack later this year as a series of services allowing you to build a full Q&A/dialog applica…

I find it terribly confusing. It does not explain what instances are, do I need an instance to access some of the services? I just want to access some services via API from my own servers. I think the documentation is not that good, there should be curl examples at least. For instance, for the STT or TTS include some curl examples. Does the STT have speaker identification or does it output text in one stream? I tried…

Yes, the API credentials for the service are different from the Bluemix login. To get the API credentials, you have to create a service through Bluemix, bind it to a Bluemix application and get the credentials from the VCAP_SERVICES of that Bluemix app. There's a getting started page describing these steps at http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercl... (We hope to make this process simpler in the future!)

Re: New services expand IBM Watson capabilities to images, speech, and more

#92

Post by anonymfus » Thu, Feb 05, 2015, 9:57 PM UTC

pesenti wrote: post #40

qeorge wrote: post #36

I've been uploading the easiest photos I can find to the visual recognition demo[1], and its yet to get one right. For example, I searched Google for "photo of girl", and found this image which seems very easy: http://www.wagggsworld.org/shared/uploads/img/rachel-s-p-pho... Watson says: Color 71% Human 67% Photo 65% Dog 59% Person 57% Placental_Mammal 56% Animal 50% Long_Jump 50% Huh? This isn't me cherry picking bad…

The top 3 classes in your example are actually correct - it is a color photo of a human. But we expect it to get much better over time. Only real world usage will allow us to make real improvement - and that's why we are eager to release early. We are also believe that the first applications (e.g., classifying animals or plants or landmarks in dedicated apps) will have narrower use case that give better accuracy.

Why confidence that it is a human is higher than confidence that it is a placental mammal, and confidence that it is a placental mammal is higher than confidence that it is an animal? More specific descriptions must have less confidence.

Or Watson is not confident that humans are placental mammals and placental mammals are animals?

Re: New services expand IBM Watson capabilities to images, speech, and more

#93

Post by Caligula » Thu, Feb 05, 2015, 10:07 PM UTC

jsstylos wrote: post #91

Caligula wrote: post #90

Earlier quoted context omitted.

I find it terribly confusing. It does not explain what instances are, do I need an instance to access some of the services? I just want to access some services via API from my own servers. I think the documentation is not that good, there should be curl examples at least. For instance, for the STT or TTS include some curl examples. Does the STT have speaker identification or does it output text in one stream? I tried…

Yes, the API credentials for the service are different from the Bluemix login. To get the API credentials, you have to create a service through Bluemix, bind it to a Bluemix application and get the credentials from the VCAP_SERVICES of that Bluemix app. There's a getting started page describing these steps at http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercl... (We hope to make this process simpler in the…

Thanks. Also, Does the STT have speaker identification/diaritization or does it output all merged text in one stream?

Re: New services expand IBM Watson capabilities to images, speech, and more

#94

Post by Caligula » Thu, Feb 05, 2015, 10:15 PM UTC

jsstylos wrote: post #91

Caligula wrote: post #90

Earlier quoted context omitted.

I find it terribly confusing. It does not explain what instances are, do I need an instance to access some of the services? I just want to access some services via API from my own servers. I think the documentation is not that good, there should be curl examples at least. For instance, for the STT or TTS include some curl examples. Does the STT have speaker identification or does it output text in one stream? I tried…

Yes, the API credentials for the service are different from the Bluemix login. To get the API credentials, you have to create a service through Bluemix, bind it to a Bluemix application and get the credentials from the VCAP_SERVICES of that Bluemix app. There's a getting started page describing these steps at http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercl... (We hope to make this process simpler in the…

Also in terms of usage, If we are using STT, how many simultaneous jobs can run on one watson app/service? Or is it a 1-1 ratio?

Re: New services expand IBM Watson capabilities to images, speech, and more

#95

Post by davegolland » Thu, Feb 05, 2015, 10:17 PM UTC

Interesting! We over at Prismatic released our interest tagging API just yesterday ( http://blog.getprismatic.com/interest-graph-api/ ). Seems like there's a lot of opening up APIs going around.

Re: New services expand IBM Watson capabilities to images, speech, and more

#96

Post by germanattanasio » Thu, Feb 05, 2015, 10:33 PM UTC

Caligula wrote: post #93

jsstylos wrote: post #91

Earlier quoted context omitted.

Yes, the API credentials for the service are different from the Bluemix login. To get the API credentials, you have to create a service through Bluemix, bind it to a Bluemix application and get the credentials from the VCAP_SERVICES of that Bluemix app. There's a getting started page describing these steps at http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercl... (We hope to make this process simpler in the…

Thanks. Also, Does the STT have speaker identification/diaritization or does it output all merged text in one stream?

The code that is being used in the demo: https://speech-to-text-demo.mybluemix.net

is in the watson-developer-cloud organization in github: https://github.com/watson-developer-cloud/speech-to-text-nod...

In fact, all the samples have the code there.

Re: New services expand IBM Watson capabilities to images, speech, and more

#97

Post by picheny » Thu, Feb 05, 2015, 10:41 PM UTC

bane wrote: post #79

qeorge wrote: post #36

I've been uploading the easiest photos I can find to the visual recognition demo[1], and its yet to get one right. For example, I searched Google for "photo of girl", and found this image which seems very easy: http://www.wagggsworld.org/shared/uploads/img/rachel-s-p-pho... Watson says: Color 71% Human 67% Photo 65% Dog 59% Person 57% Placental_Mammal 56% Animal 50% Long_Jump 50% Huh? This isn't me cherry picking bad…

The problem with AI systems has almost always been that they tend to be both right and wrong in ways that humans would never be. Watson gives high confidence to it being a color photo of a human (which is a Person, and an Animal). Which is right. But the only part that a human would ever really care about is that there's another human in the picture. It gets things wrong with a reasonable confidence for Dog, Placenta…

One thing a machine learning system can do that any one human cannot do is ingest lots of data. For example, for some tasks in which I have tried to compare human vs machine speech recognition performance the machine actually does better because the machine may - for example - know a singer's name that an individual human may not recognize.

Re: New services expand IBM Watson capabilities to images, speech, and more

#98

Post by Patrick_Devine » Thu, Feb 05, 2015, 11:02 PM UTC

qeorge wrote: post #36

I've been uploading the easiest photos I can find to the visual recognition demo[1], and its yet to get one right. For example, I searched Google for "photo of girl", and found this image which seems very easy: http://www.wagggsworld.org/shared/uploads/img/rachel-s-p-pho... Watson says: Color 71% Human 67% Photo 65% Dog 59% Person 57% Placental_Mammal 56% Animal 50% Long_Jump 50% Huh? This isn't me cherry picking bad…

I gave it a picture of a cat (http://upload.wikimedia.org/wikipedia/commons/2/22/Turkish_V...) and got:

Photo 75% Shoes 69% Nature_Scene 69% Meat_Eater 63% Object 63% Mammal 63% Vertebrate 63% Cat 63% Indoors 62% Room 60% Person 58% Color 57% Judo 54% Person_View 53% Human 51% Leisure_Activity 50%

If you give the classifier a hint (animal) it gives: Meat_Eater 63% Mammal 63% Vertebrate 63% Cat 63%

So, clearly needs work as a general classifier, but still potentially useful.

Re: New services expand IBM Watson capabilities to images, speech, and more

#99

Post by vaibhava72 » Thu, Feb 05, 2015, 11:46 PM UTC

Caligula wrote: post #93

jsstylos wrote: post #91

Earlier quoted context omitted.

Yes, the API credentials for the service are different from the Bluemix login. To get the API credentials, you have to create a service through Bluemix, bind it to a Bluemix application and get the credentials from the VCAP_SERVICES of that Bluemix app. There's a getting started page describing these steps at http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercl... (We hope to make this process simpler in the…

Thanks. Also, Does the STT have speaker identification/diaritization or does it output all merged text in one stream?

At present it does not do diarization, all text is output in one stream.

Re: New services expand IBM Watson capabilities to images, speech, and more

#100

Post by enricobruschini » Fri, Feb 06, 2015, 12:57 AM UTC

I've been developing a product with Watson from within the Partner Ecosystem, some of those capabilities are pretty useful. Others, sometimes, are kind of confusing, creating a broad overpopulated constellation of Watson-based APIs inside Bluemix.