28 votes
Accepted

Is there any research on the development of attacks against artificial intelligence systems?

Yes, there is some research on this topic, which can be called adversarial machine learning, which is more an experimental field. An adversarial example is an input similar to the ones used to train ...
  • 35.6k
12 votes

Is there any research on the development of attacks against artificial intelligence systems?

Sometimes if the rules used by an AI to identify characters are discovered, and if the rules used by a human being to identify the same characters are different, it is possible to design characters ...
  • 363
11 votes

Is there any research on the development of attacks against artificial intelligence systems?

Yes there are, for instance one pixel attacks described in Su, J.; Vargas, D.V.; Kouichi, S. One pixel attack for fooling deep neural networks. arXiv:1710.08864 One pixels attacks are attacks in ...
5 votes

Is there any research on the development of attacks against artificial intelligence systems?

Here's an example: How to hack your face to dodge the rise of facial recognition tech In his recent book The Fall, Stephenson wrote about smartglasses that that project a pattern over the facial ...
  • 6,107
4 votes

How to detect when human voice / speech appears in an microphone stream?

Your problem is an old one. There are many methods, referred to as Voice Activity Detection (VAD) methods, which detect speech from an audio signal. The typical design of a VAD algorithm follows one ...
4 votes

Is there any research on the development of attacks against artificial intelligence systems?

There are many insightful comments and answers so far. I want to illustrate my idea of "color blindness test" more. Maybe it's a hint to lead us to the truth. Imagine there are two people here. One ...
  • 403
4 votes

Is there any research on the development of attacks against artificial intelligence systems?

Isn't that essentially what chess does? For example, A human can recognize that a Ruy exchange offers white great winning chances (because of pawn structure) by move 4 while an engine would take ...
3 votes

Can variations in microphones used in training set and test set impact the accuracy of speech recognition models?

Yes it can. However, other differences between training and test data with audio could have greater effect: Identity of the speaker (including effects from gender, age, physical build, local accent, ...
3 votes

Is there any research on the development of attacks against artificial intelligence systems?

Here's a live demo: https://www.labsix.org/physical-objects-that-fool-neural-nets/ Recall that neural nets are trained by feeding in the training data, evaluating the net, and using the error between ...
  • 131
3 votes
Accepted

How to do speech recognition on a single word

If you have fixed length speech data you can detect the content using only CNN. You can see that problem as a binary classification (1 if the spoken word is correct,...
  • 2,589
3 votes
Accepted

Is music/sound similarity comparison feasible on neural networks?

Yes, it is possible, even if the best approach could be different from neural networks. Anyway, you should extract some significant features from the audio (energy, onsets, root frequencies, and ...
  • 146
3 votes
Accepted

What is easier or more efficient to summarize voice or text? [DP/RN]

Summarizing text is always going to be 'easier or more efficient' than voice simply because voice requires the additional step of converting to text. That doesn't tell you anything about accuracy. ...
2 votes
Accepted

Has there been research done regarding processing speech then building a "speaker profile" based off the processed speech?

Yes, there is. A quick search found this: Multimodal Speaker Identification Based on Text and Speech (2008). In the abstract, they write This paper proposes a novel method for speaker identification ...
  • 36
2 votes

How does Wit.ai convert sentences into structured data?

I can't speak to wit.ai specifically, but I can tell you a little bit about how similar applications work. Specifically, I can talk a bit about Apache Stanbol which also converts free text into ...
  • 3,697
2 votes
Accepted

Why is the short-time Fourier transform used for preprocessing audio samples?

Fourier transform is used to transform audio data to get more information (features). For example, raw audio data usually represented by a one-dimensional array, ...
  • 2,589
2 votes

Is there any research on the development of attacks against artificial intelligence systems?

There are some research at least on the "foolability" of neural networks, that gives insight on potential high risk of neural nets even when they "seem" 99.99% acurate. A very good paper on this is ...
2 votes
Accepted

AI natural voice generator

The reason for robot like speech may be because tacotron uses griffin lim for vocoder, which cannot reproduce sound with perfection, often introducing robot like sound artifects. A vocoder is a ...
  • 1,725
1 vote
Accepted

How to define a loss function for multi-label problem?

Given your response in the comments, you are faced with a semi-supervised learning problem where you have a small set of data with ground truth labels, and a large set of data without ground truth ...
1 vote

How to define a loss function for multi-label problem?

If I understand correctly, the training data are voice messages which contain one or more suggested labels for the class that the voice message belongs to. Even though there are multiple suggestions, ...
  • 21
1 vote

Deep audio fingerprinting for word search

You would need to perform some kind of speech-to-text to get the audio transcription with the corresponding synchronization wrt the audio. Then search in the ...
1 vote

"Vocal captcha" for robots on the phone?

your question is a very similar to "turing-test". you could narrate a simple story and ask questions based on that , considering the state-of-art algorithms in "question-answering" are still far ...
1 vote
Accepted

How much the dialects recognition and speech recognition are relevant?

The tutorials you link are not much relevant, there are already existing implementations of your exact problem. You can use https://github.com/swshon/dialectID_e2e, there are many other similar ...
1 vote

Can variations in microphones used in training set and test set impact the accuracy of speech recognition models?

The most usual differences in signal records caused by different microphones will have small if not null impact in the recognition accuracy, in particular if we are talking about changes one mic by ...
1 vote

Splitting audio consisting of male / female speaker into segments

Edit: It's not clear what exactly you're trying to accomplish... My answer assumes you wanted to split the man and the woman's audio, but re-reading your question make me think otherwise. Note: Don'...
  • 11
1 vote

Has there been research done regarding processing speech then building a "speaker profile" based off the processed speech?

Speaker identification is quite widely researched domain. Modern approach would be to map speaker information to i-vector, a real-valued vector of 200-400 components that characterizes speaker fully. ...

Only top scored, non community-wiki answers of a minimum length are eligible