Develop Reference

Android Compare two sounds [duplicate]

I am working on one voice messaging application, I need to compare two voice like,
Register with app by record your voice
Sent voice message to
another user by record voice, but first need to compare this voice
to recorded voice in profile.
Its for security purpose and need to know recorded message is from specific user or not.
I tried :
Compare two sound in Android
http://www.dreamincode.net/forums/topic/274280-using-fft-to-compare-two-audio-files-and-then-realtime-comparison/
But not getting idea about voice Comparison.
Please share if anybody know about the same. Didn't find any sample to do this.

Since you indicated it's for security purpose, I'd like to first share a few things on voice biometry :-)
The problem with authenticating someone is that you'd need to be sure he was actually there saying the things that were recorded... and that's a whole different level of complexity than merely comparing voice characteristics.
Algorithms extracting voice features from a sample and later calculating the distance between a new sample and the first one can easily be fooled by a recording made up by an attacker.
Since in your case there's a human recipient, creating a message made up of chopped words or sentences from random conversations is actually quite difficult and time consuming. But not completely impossible...
There are very good sounding softwares created for the music industry that will e.g. take some voice audio input and make it sound (intonation and time wise) like a second audio sample (a guide, made by the fraudster). Vocalign Pro by SynchroArts does this to help get perfect backing vocal tracks. You could further tweak the audio by hand using other voice editing softwares and achieve an acceptable level of quality that wouldn't be immediately detected by the recipient.
Depending on what the attacker wants your user to say, the process complexity could range from an hour to a day provided he has all the recording material he wants...
To fight against this type of attack, you need to detect the audio sample has been edited. The digital edition will leave unnatural traces. E.g. in the background noise surrounding the voice.
AFAICT, only the best commercial softwares achieve this level security check, but I can't tell how far they go in the detection of such edits.
From a pure security perspective, you'd also need to be sure the device was not compromised. So these voice verification check should happen server side and not on the phone itself.
Please note these are general considerations and it all depends on what sort of security measures you actually need for your use case. My car alarm is certainly not unbreakable but it helps raising the bar so fewer attackers could potentially steal it...
Another thing to consider is that biometry is by definition a statistical process and it will yield a certain percentage of false positives and false negatives. By changing the acceptance threshold, you'll be able to lower one of them at the cost of raising the other.
Selecting an appropriate threshold will require you to have a fair amount of test data. Say 1 minute recording of at least 200 speakers to start getting a picture.
One more thing I think you'll need to consider is the inherent variability of the human voice. People may be sick which in some cases might render the voice unrecognizable. Also the emotional state might play a role: sadness or anger will yield different sounding voices...
And last but not least, the surrounding noise might pose a problem. Say the user enrolled while at home and later records a message while on the go in a busy city environment, the system might have troubles making sure it's actually the same person speaking. The signal to noise ratio is definitely going to be one of your main issues. Small tip: depending on the distance of the microphone to the mouth, the ratio will be quite different. You'll get way better result when the user puts the phone close to its face like in a regular phone conversation than when the user looks at the screen while recording the message.
Voice variability and signal to noise ratio are probably the main reasons behind false negative results.
Hopefully, you now have a better understanding of the challenges awaiting you and I can start sharing some pointers for open source and commercial libraries.
AFAIK, there are no open source libraries that includes fraudster detection...
You may want to check Nuance Communication for state-of-the-art. There are plenty other vendors, just check with Google, I only mentioned Nuance because of it's reputation.
There is an OSS library called Alize (written in C++, under LGPL license) which uses an algorithm called MFCC (Mel Frequency Cepstrum Coefficients). MFCC is known to bring excellent results. Expect a steep learning curve as this software is aimed at researchers willing to improve the state-of-the-art on this topic and the vocabulary used is very specific.
I wrote an OSS library named Recognito (Java, Apache 2.0) aimed at regular developers so you should be able to test it in a matter of minutes. The lib is very young and I first focused on it's API before improving the algorithms. The algorithm I use for the moment is called Linear Predictive Coding (LPC) and is known to bring good results (and I do have good results, provided recordings yield the same level of quality :-)). I'm currently in the process of releasing a new version including a likelihood coefficient in the match results. MFCC implementation is on the road map.
There is plenty of javadoc and the code should be very straightforward...
https://github.com/amaurycrickx/recognito
Recognito has a dependency on javax.sound packages for audio file handling. You may want to check this post for what it takes to use it in Android: Voice matching in android
Given many people need something for android, I'll do something about it in the near future instead of saying how one should modify the lib :-)
HTH

Real-time call transcription on Android

I am an Android developer who is living with hearing impairment and I am currently exploring the option of making a speech to text app with Speech Recognizer API in Android. Closed-captioning telephones and Innocaption are not available in in my home country. Potential applications might be like captioning during telephone calls.
https://developer.android.com/reference/android/speech/SpeechRecognizer.html
The API is meant for capturing voice commands, not for real-time live transcribing. I am even able to implement it as a service but I constantly need to restart it after it has delivered a result or a partial result, which is not feasible in a conversational setting (words get lost while the service is restarting).
Do note that I don't need a 100% accuracy for this app. Many hearing impaired people find it helpful to have some context of the conversation to help them along. So I don't actually need comments about how this is not going to be accurate.
Is there a way to implement Speech Recognizer in a continuous mode? I can create a textview that constantly updates itself when new text is returned from the service. If this API is not what I should be looking at, is there any recommendation? I tested CMUSphinx but find that it is too dependent on blocks of phrases/sentences that it is not likely to work for the kind of application I have in mind.

I am a deaf software developer, so I can chime in. I've been monitoring the state of art of Speech-To-Text APIs, and the APIs have now become "good enough" to provide operatorless relay/captioning services for CERTAIN kinds of phone conversations with people using telephone in quiet settings. For example, I get 98% transcription accuracy with my spouse's voice with the Apple Siri realtime transcription (iOS 8).
I was able to jerryrig phone captioning by routing the sound out of one phone, to a 2nd iPhone that I press the microphone button (popup keyboard), and successfully captioned a telephone conversation with ~95% accuracy at 250 words per minute (faster than Sprint Captioned Telephone and Hamilton Captioned Telephone), at least until the 1 minute cutoff time.
Thusly, I declare computer-based voice recognition practical for phone calls with family members (of the type you call frequently in quiet environments), where you can at least coach them to move to a quiet place to allow captioning to work properly (with >95% accuracy). Since iOS 8 got released, we REALLY need this, so we don't need to rely on rely operators or captioning telephone. Sprint Captioned telephone lags badly during fast speech, while Apple Siri keeps up, so I can conduct more natural telephone conversations with my jerryrigged two-iOS-device Apple Siri "realtime Captioned Telephone" setup.
Some cellphones transmit audio in a higher-def manner, so it works well between two iPhones (iPhone speaker piped into another iPhone's Siri running in iOS8 continuous mode). That's assuming you're on G.722.2 (AMR-WB), like when running two iPhones on the same carrier that supports the high-def audio telephony standard. It works perfectly when piped through Siri -- roughly as good as doing it in front of the phone, for the same human voice (assuming the other end is speaking into the phone in a quiet environment).
Google and Apple needs to open up their speech-to-text APIs to assistive applications, pronto, because operatorless telephone transcription is finally now practical, at least when calling family members (good voices & coached to be in a quiet environment when receiving call). The continuous recognition time limit needs to also be removed during this situation, too.

Google is not going to work with telephone quality audio anyway, you need to work on captioning service using CMUSphinx yourself.
You probably didn't configure CMUSphinx properly, it should be ok for large vocabulary transcription, the only thing you should care about is to use telephony 8khz model, not wideband model and generic language model.
For the best accuracy it's probably worth to move processing on the server, you can setup the PBX to make the calls and transcribe audio there instead of hoping to do something on a limited device.

It is true that the SpeechRecognizer API documentation claims that
The implementation of this API is likely to stream audio to remote
servers to perform speech recognition. As such this API is not
intended to be used for continuous recognition, which would consume a
significant amount of battery and bandwidth.
This bit of text was added a year ago (https://android.googlesource.com/platform/frameworks/base/+/2921cee3048f7e64ba6645d50a1c1705ef9658f8). However, no changes were made to the API at the time, i.e. the API remained the same. Also, I don't really see anything specific to networking and battery drain in the API documentation. So, go ahead and implement a recognizer (maybe based on CMUSphinx) and make it accessible via this API.

Compare two voice in android

I am working on one voice messaging application, I need to compare two voice like,
Register with app by record your voice
Sent voice message to
another user by record voice, but first need to compare this voice
to recorded voice in profile.
Its for security purpose and need to know recorded message is from specific user or not.
I tried :
Compare two sound in Android
http://www.dreamincode.net/forums/topic/274280-using-fft-to-compare-two-audio-files-and-then-realtime-comparison/
But not getting idea about voice Comparison.
Please share if anybody know about the same. Didn't find any sample to do this.

Since you indicated it's for security purpose, I'd like to first share a few things on voice biometry :-)
The problem with authenticating someone is that you'd need to be sure he was actually there saying the things that were recorded... and that's a whole different level of complexity than merely comparing voice characteristics.
Algorithms extracting voice features from a sample and later calculating the distance between a new sample and the first one can easily be fooled by a recording made up by an attacker.
Since in your case there's a human recipient, creating a message made up of chopped words or sentences from random conversations is actually quite difficult and time consuming. But not completely impossible...
There are very good sounding softwares created for the music industry that will e.g. take some voice audio input and make it sound (intonation and time wise) like a second audio sample (a guide, made by the fraudster). Vocalign Pro by SynchroArts does this to help get perfect backing vocal tracks. You could further tweak the audio by hand using other voice editing softwares and achieve an acceptable level of quality that wouldn't be immediately detected by the recipient.
Depending on what the attacker wants your user to say, the process complexity could range from an hour to a day provided he has all the recording material he wants...
To fight against this type of attack, you need to detect the audio sample has been edited. The digital edition will leave unnatural traces. E.g. in the background noise surrounding the voice.
AFAICT, only the best commercial softwares achieve this level security check, but I can't tell how far they go in the detection of such edits.
From a pure security perspective, you'd also need to be sure the device was not compromised. So these voice verification check should happen server side and not on the phone itself.
Please note these are general considerations and it all depends on what sort of security measures you actually need for your use case. My car alarm is certainly not unbreakable but it helps raising the bar so fewer attackers could potentially steal it...
Another thing to consider is that biometry is by definition a statistical process and it will yield a certain percentage of false positives and false negatives. By changing the acceptance threshold, you'll be able to lower one of them at the cost of raising the other.
Selecting an appropriate threshold will require you to have a fair amount of test data. Say 1 minute recording of at least 200 speakers to start getting a picture.
One more thing I think you'll need to consider is the inherent variability of the human voice. People may be sick which in some cases might render the voice unrecognizable. Also the emotional state might play a role: sadness or anger will yield different sounding voices...
And last but not least, the surrounding noise might pose a problem. Say the user enrolled while at home and later records a message while on the go in a busy city environment, the system might have troubles making sure it's actually the same person speaking. The signal to noise ratio is definitely going to be one of your main issues. Small tip: depending on the distance of the microphone to the mouth, the ratio will be quite different. You'll get way better result when the user puts the phone close to its face like in a regular phone conversation than when the user looks at the screen while recording the message.
Voice variability and signal to noise ratio are probably the main reasons behind false negative results.
Hopefully, you now have a better understanding of the challenges awaiting you and I can start sharing some pointers for open source and commercial libraries.
AFAIK, there are no open source libraries that includes fraudster detection...
You may want to check Nuance Communication for state-of-the-art. There are plenty other vendors, just check with Google, I only mentioned Nuance because of it's reputation.
There is an OSS library called Alize (written in C++, under LGPL license) which uses an algorithm called MFCC (Mel Frequency Cepstrum Coefficients). MFCC is known to bring excellent results. Expect a steep learning curve as this software is aimed at researchers willing to improve the state-of-the-art on this topic and the vocabulary used is very specific.
I wrote an OSS library named Recognito (Java, Apache 2.0) aimed at regular developers so you should be able to test it in a matter of minutes. The lib is very young and I first focused on it's API before improving the algorithms. The algorithm I use for the moment is called Linear Predictive Coding (LPC) and is known to bring good results (and I do have good results, provided recordings yield the same level of quality :-)). I'm currently in the process of releasing a new version including a likelihood coefficient in the match results. MFCC implementation is on the road map.
There is plenty of javadoc and the code should be very straightforward...
https://github.com/amaurycrickx/recognito
Recognito has a dependency on javax.sound packages for audio file handling. You may want to check this post for what it takes to use it in Android: Voice matching in android
Given many people need something for android, I'll do something about it in the near future instead of saying how one should modify the lib :-)
HTH

Detect the beginning of a sound or voice in Android

I would like to listen to the mic (I guess using AudioRecord) and perform some action the very moment a person starts to speak. I know I can buffer audio with AudioRecord, but how do I analyze it ?

Well, the difficult part will be getting the phone to recognize that it's voice. You can set the voice recognition system as the input, instead of the mic, which might be able to do that. I don't think so though, because (I actually read all about this yesterday) the phone doesn't actually do the recognizing, it just opens up a live stream (like a phone call) to the Google servers, and they do the recognizing.
Also, the information that I have found so far points to the conclusion that Android does not support analysis of live audio from the mic. All these other apps that seem to be "live" are actually just taking a bunch of small samples and analyzing them really quickly so that they seem live. A 500 millisecond sample every 300 milliseconds seems to be common.
Luckily, on the side of my programming job, I'm also a sound technician, so I can tell you that (if you were willing to put in the work) there is a way to detect actual voice as opposed to just sound. Every voice is split into a few distinct ratios of frequencies which all combine to make the voice we hear, and every voice's ratios remains pretty constant, while each individual voice's ratios are different (which is why voice-based passwords work). So, if you were able to take a sample, break it up into frequencies of about 10hz each, and watch for the amplitude of each, and when you got a frequency/amplitude pattern that looked similar to a voice instead of just "white noise", you'd be in business. DOING that however, doesn't seem like it'd be easy at all. Something similar has been done before with the app called SpectralView, which displays the audio spectrum all broken up.
Also, as you can see by using the Voice Search, a voice also fluctuates a lot in how loud it is. You could look for that, but it wouldn't be as reliable.
In conclusion, how do you analyze it? Well, you would have to look for a pattern in the frequencies that looks like a voice. How do you do that? Well, to be honest, I don't know for sure. Sorry.

Microphone input

I'm trying to build a gadget that detects pistol shots using Android. It's a part of a training aid for pistol shooters that tells how the shots are distributed in time and I use a HTC Tattoo for testing.
I use the MediaRecorder and its getMaxAmplitude method to get the highest amplitude during the last 1/100 s but it does not work as expected; speech gives me values from getMaxAmplitude in the range from 0 to about 25000 while the pistol shots (or shouting!) only reaches about 15000. With a sampling frequency of 8kHz there should be some samples with considerably high level.
Anyone who knows how these things work? Are there filters that are applied before registering the max amplitude. If so, is it hardware or software?
Thanks,
/George

It seems there's an AGC (Automatic Gain Control) filter in place. You should also be able to identify the shot by its frequency characteristics. I would expect it to show up across most of the audible spectrum, but get a spectrum analyzer (there are a few on the app market, like SpectralView) and try identifying the event by its frequency "signature" and amplitude. If you clap your hands what do you get for max amplitude? You could also try covering the phone with something to muffle the sound like a few layers of cloth

It seems like AGC is in the media recorder. When I use AudioRecord I can detect shots using the amplitude even though it sometimes reacts on sounds other than shots. This is not a problem since the shooter usually doesn't make any other noise while shooting.
But I will do some FFT too to get it perfect :-)

Sounds like you figured out your agc problem. One further suggestion: I'm not sure the FFT is the right tool for the job. You might have better detection and lower CPU use with a sliding power estimator.
e.g.
signal => square => moving average => peak detection
All of the above can be implemented very efficiently using fixed point math, which fits well with mobile android platforms.
You can find more info by searching for "Parseval's Theorem" and "CIC filter" (cascaded integrator comb)

Sorry for the late response; I didn't see this question until I started searching for a different problem...
I have started an application to do what I think you're attempting. It's an audio-based lap timer (button to start/stop recording, and loud audio noises for lap setting). It' not finished, but might provide you with a decent base to get started.
Right now, it allows you to monitor the signal volume coming from the mic, and set the ambient noise amount. It's also using the new BSD license, so feel free to check out the code here: http://code.google.com/p/audio-timer/. It's set up to use the 1.5 API to include as many devices as possible.
It's not finished, in that it has two main issues:
The audio capture doesn't currently work for emulated devices because of the unsupported frequency requested
The timer functionality doesn't work yet - was focusing on getting the audio capture first.
I'm looking into the frequency support, but Android doesn't seem to have a way to find out which frequencies are supported without trial and error per-device.
I also have on my local dev machine some extra code to create a layout for the listview items to display "lap" information. Got sidetracked by the frequency problem though. But since the display and audio capture are pretty much done, using the system time to fill in the display values for timing information should be relatively straightforward, and then it shouldn't be too difficult to add the ability to export the data table to a CSV on the SD card.
Let me know if you want to join this project, or if you have any questions.