Profile

Cover photo
Nickolay Shmyrev
Lives in Москва
403 followers|155,507 views
AboutPosts+1's

Stream

Nickolay Shmyrev

Shared publicly  - 
 
Nice things going on the other side of the world

http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/ASR-events-OC16-details
OC16 MixASR-CHEN Challenge. The OC16 MixASR-CHEN challenge is part of the special session "mixlingual speech processing" on O-COCOSDA 2016. The challenge is a Chinese-English mixed speech recognition task, where the host and embedding languages are Chinese and English respectively.
1
Add a comment...

Nickolay Shmyrev

Shared publicly  - 
1
Dirk Schnelle-Walka's profile photo
 
Indeed. It took then quite some time to catch up with that "new" technology. However, I think that they have enough material to easily support many languages. This is their major advantage, still. I wonder how much they can really rely on it. Several other players appeared on the market, already. 
Add a comment...

Nickolay Shmyrev

Shared publicly  - 
 
Last year I've got quite many requests to decode speech captchas. Most of them are simply noise-corrupted digits. Attackers record thousands of samples and then feed them into adaptation and despite you have some noise, you still get a very good decoding rate up to 90%. Even reCaptcha does this.

Please stop using digits in speech captchas, try large vocabulary instead. Use music on background, not simply noise (and very diverse music, singe melody can be easily learned). Or, better, don't use captchas at all, they are really annoying and do not protect anything.
5
1
Daniel Povey's profile photoPatrick Nguyen's profile photoAhmet A. Akın's profile photoTal Weiss's profile photo
4 comments
 
Is there a lot of money in it? Asking for a friend 😎
Add a comment...

Nickolay Shmyrev

Shared publicly  - 
 

Nice project to explain machine learning classifiers

https://github.com/marcotcr/lime

2
Add a comment...

Nickolay Shmyrev

Shared publicly  - 
 
It seems that people will loose the ability to read, comprehend and remember long texts soon, the question now is - is it possible to deliver very complex messages without texts?

The critical issue is to design a flow of information into human brain which will both allow to scan though extremely large amounts of data and deduct new meanings. Text/speech is indeed quite slow channel for that, vision might be reasonable.

Visualization seems relevant if we want to keep human intelligence instead of replacing it with pure computer intelligence. Works like LargeVis

Visualizing Large-scale and High-dimensional Data
by Jian Tang, Jingzhou Liu, Ming Zhang, Qiaozhu Mei

are much more important then. See also the LargeVis project on github.
It seems that people will loose the ability to read, comprehend and remember long texts soon, the question now is - is it possible to deliver very complex messages without texts? The critical issue is to design a flow of information into human brain which will both allow to scan though extremely ...
1
Add a comment...

Nickolay Shmyrev

Shared publicly  - 
 
New methods to process information will result in new hardware architectures which will be order of magnitude more efficient and scalable. The core idea to explore here is data locality, you store the data in a simple cell and you process the data in the same cell. Only communication is a limiting factor then

http://journal.frontiersin.org/article/10.3389/fnins.2016.00333/full
1
Add a comment...

Nickolay Shmyrev

Shared publicly  - 
 
Microsoft is doing nice work on speech API design in UW framework, for example, they removed grammars with repeats and loops and introduced constrains. A list of example phrases could be a constrain. Nice.
A constraint for a SpeechRecognizer object based on a list of words or phrases. When initialized, this object is added to the Constraints collection. Constraints, or grammars, define the spoken words and phrases that can be matched by the speech recognizer. You can specify one of the pre-defined ...
1
Add a comment...
In his circles
157 people
Have him in circles
403 people
NEHAL SIROYA's profile photo
Ido Shapira's profile photo
Al Zatv's profile photo
Иван Бондаренко's profile photo
Amaury Crickx's profile photo
Leo Hämäläinen's profile photo
Sergio Kviato's profile photo
James Ellis's profile photo
Satinderpal Singh's profile photo

Nickolay Shmyrev

Shared publicly  - 
 
This is quite an important paper on "model-free" learning. The idea is that you can learn from very few examples, but you should memorize all previous inputs.
 
Reinforcement learning that uses random projections to speed up policy computations, I like it. Model-Free Episodic Control by Charles Blundell, Benigno Uria, Alexander Pritzel, Yazhe Li, Avraham Ruderman, Joel Z Leibo, Ja...
View original post
1
Add a comment...

Nickolay Shmyrev

Shared publicly  - 
Today, a friend asked me for help figuring out how to calculate the standard deviation over a discrete probability distribution. I pulled up my notes from college and was able to correctly calculate the standard deviation they had been unable to derive after hours upon hours of searching the ...
1
Add a comment...

Nickolay Shmyrev

Shared publicly  - 
 
This paper considers an important problem of properly rejecting unknown inputs. Overall vision researchers are quite ahead of speech researchers.
 
What do you really know?
Abstract: Deep networks have produced significant gains for various visual recognition problems, leading to high impact academic and commercial applications. Recent work in deep networks highlighted that it is easy to generate images that humans would never classify as a particular object class, ...
View original post
1
Add a comment...

Nickolay Shmyrev

Shared publicly  - 
 
Colors of the Math is interesting overall, and more exciting it has a chunk on cocktail party problem. Aaditya V. Rangan claims it is "solved" ;). He probably meant DUET method that separates sources blindly in phase/amplitude diagram. Phase is really idea, unused for now.

https://www.youtube.com/watch?v=doYxTQMNnDs
 ·  Translate
1
Add a comment...

Nickolay Shmyrev

Shared publicly  - 
 
I wonder what happened in Google speech API, did they lost half of their servers? http://stackoverflow.com/questions/38150312/google-speech-recognition-timeout
1
Add a comment...
People
In his circles
157 people
Have him in circles
403 people
NEHAL SIROYA's profile photo
Ido Shapira's profile photo
Al Zatv's profile photo
Иван Бондаренко's profile photo
Amaury Crickx's profile photo
Leo Hämäläinen's profile photo
Sergio Kviato's profile photo
James Ellis's profile photo
Satinderpal Singh's profile photo
Contact Information
Home
Email
Places
Map of the places this user has livedMap of the places this user has livedMap of the places this user has lived
Currently
Москва
Previously
Астрахань
Basic Information
Gender
Male
Other names
Николай Шмырёв
Nickolay Shmyrev's +1's are the things they like, agree with, or want to recommend.
Unsupervised Feature Selection on Data Streams / Streaming Anomaly Detec...
nuit-blanche.blogspot.com

Today, we see the use of streaming algorithms to figure out anomaly detection or unsupervised feature selection. Streaming Anomaly Detection

Solving the Cocktail Party Problem with a 3D Printed Metamaterial Disc
3dprint.com

If you have ever tried to give vocal directions to your smartphone while amidst a group of voices, you know how hard it is for a computer to

Neural Word Embeddings as Implicit Matrix Factorization
nuit-blanche.blogspot.com

Recently at the Paris Machine Learning meetup there was a brief presentation on Word2Vec by Charles Ollion. Well, I was wondering about the

How Crowdsourcing Will Help Startups Build Their Own Versions of Siri | ...
www.wired.com

Speech recognition is hard, even for the world’s largest tech companies. Apple and Google draw on massive collections of recordings of real

Interspeech 2014 Recap
spokenlanguageprocessing.blogspot.com

This year's Interspeech was in Singapore. Singapore is, in some ways, a very easy venue to travel to. It's a modern, cosmopolitan city. They

Miro
market.android.com

This magic mirror loves you. You are the most beautiful girl on the world for him. He will try to satisfy your most crazy desires, just ask

Theory of Convex Optimization for Machine Learning / Estimation in high ...
nuit-blanche.blogspot.com

Sebastien Bubeck just came out with a monograph on the Theory of Convex Optimization for Machine Learning while Roman Vershynin just release

Intel Pays Up To $30M For A Personal Assistant Platform From Ginger Soft...
techcrunch.com

Apple has Siri, and now Intel has Ginger. The chipmaker has made one more acquisition to bolster its advanced computing and artificial intel

Smile - Smart Photo Annotation
market.android.com

Are you tired from taking pictures and then not being able to find them in between the hundreds of pictures on your smartphone? Are you tire

Ispikit
plus.google.com

Ispikit helps you practice, assess and improve your English pronunication

With A Voice Interface API For Any App, Wit.ai Wants To Be The Twilio Fo...
techcrunch.com

Last year, voice technology giant Nuance quietly acquired VirtuOz, a developer of virtual assistants for online sales, marketing and support

​Hot. Cool. Yours. Fin! Sochi Olympics close with breathtaking show
rt.com

After two weeks of cheering, daring and record breaking, the Sochi 2014 Olympic Games finally bids farewell as athletes and fans gather one

Saturday Morning Video: Unraveling dolphin communication complexity: Pas...
nuit-blanche.blogspot.com

For some odd reason, this video from last saturday on the Analyzing Animal Vocal Sequences Investigative Workshop could not play correctly.

Chrome hack lets websites keep listening after you close the tab
www.theverge.com

Toying around with voice-recognition apps, developer Tal Ater noticed something strange. Because of a quirk in Chrome's microphone settings,

Sunday Morning Insight: Randomization is not a dirty word
nuit-blanche.blogspot.com

From [8] The recent announcement of Yann LeCun's appointment as a director of the new Artificial Intelligence Lab at Facebook and Geoff Hint

Machined Learnings: ICML 2013: Sparse, Deep, and Random
www.machinedlearnings.com

ICML 2013 was a great conference this year, kudos to the organizers. It's too big for an individual to get a comprehensive view of everythin

OpenEars 1.3.0 out now with Pocketsphinx and Sphinxbase .8 | Politepix
www.politepix.com

Sign up for the Politepix OpenEars frameworks mailing list here in order to receive infrequent notifications of when OpenEars frameworks (su

Speech recognition engine PocketSphinx landed in Ubuntu 13.10 by default...
www.iloveubuntu.net

Months ago, the developers announced and explained Ubuntu's converged vision, where a singular OS is to power phones, tablets, desktops, TVs

Deep Thoughts on ICASSP 2013
spokenlanguageprocessing.blogspot.com

ICASSP 2013 is wrapping up today in Vancouver. Unfortunately, I missed the last day (and sessions on speech synthesis and prosody that I wou

Blame the linguists!
thelousylinguist.blogspot.com

Pullum has let me down. His latest NLP lament isn’t nearly as enraging or baffling as his previous posts. I basically agree with his points