Speech Recognition: Men harder to understand than women

Researchers at Stanford University (USA) and the University of Edinburgh (UK) have tested various automatic speech recognition (ASR) systems and found that in general they have a more difficult time recognizing speech from males than females.  One of the causes mentioned by the researchers was that the men tended to use fillers such as "emm" more often.

I should point out that the tests were conducted using recordings of telephone calls.  This is important because the type of "channel" the audio is being carried over makes a significant difference to a computer-based speech recognition system.

The work was sponsored by the US Office of Naval Research.

For a quick overview of the research, you can read the BBC (center-left news media, UK) article here.

Enjoy!

Audio Forensics: Pro Tools Snow Leopard Pre-Release

I don't use Pro Tools myself, but many audio forensics professionals do, so here is a breaking news item...

From Hitsquad Musician's News:

Pro Tools Prerelease now available for Mac OS X Snow Leopard

Avid/Digidesign is pleased to announce the immediate availability of a prerelease version of Pro Tools software that provides expanded Mac OS X 10.6.x Snow Leopard compatibility to Pro Tools 8 users.

Filtering: Video clip explains Auto-Tune software

Nova's ScienceNOW by PBS (Public Broadcasting Service, USA) has an informative video clip on Andy Hildebrand's pitch-correction software called Auto-Tune. This audio filtering technology is used by professionals to correct mis-sung notes both in the studio and during live performances. It has been compared to Photoshop for voices.

Enjoy!

Computer Audio: Latest Audacity beta (1.3.7) is released

Audacity 1.3.7(beta) is available for download. This release primarily seems to consist of bug fixes, but they do say that they added support for DirectSound, which is a widely-used Windows(R) DirectX API (Application Programmer Interface). Here is the text from their announcement:

Audacity (http://audacity.sourceforge.net/) is a fast multi-track audio editor and recorder for Windows, Mac, and Linux/Unix.


The Audacity Team is pleased to announce the release of Audacity 1.3.7 (beta) for Windows, Mac and Linux/Unix. This is primarily a bug-fix release to significantly improve stability and usability, especially on Mac OS X, but includes some new features too.

Cross-Platform Bug Fixes include:

* Muting/soloing caused incorrect channel results in exported stereo files
* Fixes for Nyquist effects, Compressor and Noise Removal
* Fixed Export as WAV could be corrupted if overwriting to same file, and Export Multiple to uncompressed formats only produced 16-bit WAV
* MP3 and WMA now export correctly with all supported metadata

Platform-specific Bug Fixes include:
* Windows Vista: crash opening Preferences
* Mac OS X and Linux: fixes for spurious clipping, label typing, no shortcuts after running effects, and project rate when importing files
* Mac OS X only: fixes for inactive or corrupted menus and hidden dialogues, portable settings, and Command and Control shortcuts. Also FFmpeg installer now available.

New features/other improvements:
* F11 Full Screen mode, high-quality "Sliding Time Scale/Pitch Shift" effect, Audio Contrast Analyzer
* Windows: sound devices can now be opened using the more efficient DirectSound API
* Improved latency correction using fixed correction value

See http://audacity.sourceforge.net/ for details.

Physics: A round-up of recent interesting links!

My aplogies for my light posting of late. Outside commitments have kept me from posting nearly as much as I would like. Here is a collection of links that I have saved up over the last several weeks to blog about. I hope you enjoy them, but please note that some of these are not serious, scientific articles - just because it can be found on the Internet doesn't make it science, much less forensic science! If you are particularly interested in any of the topics addressed below, just let me know and I'll delve further in a future posting.

K-Lite codec package update

X-rays made from Scotch(R) tape (hat tip to A.A.)

Superconductivity Can Induce Magnetism

Deaf people feel their way to speech

Seeing Through The Skin: Optic-less Imaging Technology Could Beat Lens-based Imaging Devices

HOWTO read the secret forensic dots in your laser-printer output

Biometric identifcation by body language

Sound-card oscilloscope

Audio bone headphones

Scientists Watch As Listener's Brain Predicts Speaker's Words

Hidden airport scanner will pinpoint terrorists

Overpaid professions

Military camouflage

Police probe cell phones to catch criminals

How magicians control your mind

How forensic lab techniques work

Computers reassemble pieces of fractured archaeology

Review of Microsoft's Photosynth

Images of atmospheric optics

12 worst Photoshop mistakes ever

Darpa super-resolution vision technology R&D

How other senses adjust to blindness

Family name geographical profiler

Computer Audio: Pro Tools now available for Mac OS-X Leopard

Pro Tools for Leopard is out. I don't use it myself, but I know several audio forensic professionals who do and they swear by it.

Computer Audio: Latest Audacity beta is released

From the Audacity announcement:

The Audacity Team is pleased to announce the release of Audacity 1.3.5 (beta) for Windows, Mac and Linux/Unix. Changes include improvements and new features for recording, import/export and the user interface. Because it is a work in progress and does not yet come with complete documentation or translations into foreign languages, it is recommended for more advanced users. For all users, Audacity 1.2.6 is a stable release, complete and fully documented. You can have Audacity 1.2.6 and 1.3.5 installed on the same machine.

Enjoy!

Acoustic Recognition: Toward teaching a machine to label music

The New Scientist Technology Blog posts about Major Minor, an on-line music labeling game by Dan Ellis and Michael Mandell at Columbia University (USA).  The goal is to build up a database of sounds that have been tagged by users (all humans, presumably) with descriptive words.  The scoring system seems very well thought out to generate appropriate tags, weed out inappropriate ones, and to motivate participation.  

Why does the world need such a database?  Well, just like with humans, in order to teach a machine (e.g. a computer) to recognize some characteristic of a sound, you have to feed it many, many examples of sounds with that characteristic for it to learn from.  In this case, the researchers use the Internet to provide the means to efficiently and effectively get people to the "test site" and their well-constructed, slightly addictive game for the incentive to get the test subjects to willing participate and give up their neural processing time to help out.  Good luck to the team at Columbia U!

Computer Audio: Audacity 1.3.4 Released for Windows and Linux

Audacity 1.3.4 has been released for Windows and Linux - sorry, but we'll have to wait for Mac OS-X!  To download, click here (audacity.sourceforge.net).

Computer Audio and Video: Codec packs

Being able to play audio and video files, often years after they were originally created, has been a steadily growing problem for audio, video, and computer forensic examiners.

Of course, video examiners encounter this almost daily if they are dealing with security digital video recorder (DVR) files because of the proprietary codecs (which is short for COder DECoder, and is the software program that converts video to and from a particular digital file format) used by manufacturers of the systems to lock users into their brands.

Even for those who do not process security DVR every day, things have been getting worse. Part of this is due to changes in the latest Windows Media Player where Microsoft removed one of the popular codecs previously used to encode/decode AVI files. Many people are under the impression that AVI is uncompressed and either doesn't need a codec or only has one universal codec. This is far from the truth. AVI, like WAV, is a very flexible format and it supports the use of almost any audio or video codec. To play the file, you have to have the correct codec - period. No codec, no playback - it is that simple.

I was faced with this problem just recently due to the Microsoft changes. The files were uncompressed AVI and would not play on three different machines, even though they played back correctly only two months before. A bit of digging found the cause. The solution ended up being to download an audio/video codec pack. I used the free one found here, but there are others out on the Internet also.

You can imagine how this can be a problem for law enforcement where evidence may need to be archived for up to 25 years and still be able to played back. All it takes is one automatic update and the ability to playback can cease. This is why I recommend to my students that they always include a copy of a freeware player that will play back the media as part of the archived evidence.

Computer Audio: Audition 3 in the works and an audio forensics wish list

First it was a rumor and now it is confirmed - Adobe Audition 3 is in development and Adobe plans to announce more about it later this year. A search of their web site didn't yield any additional details but there is a post on Hart Shafer's blog (Hart's Audition) that confirms it and mentions that it is on a different schedule than the rest of their Creative Suite. Hart Shafer is the product manager for Adobe's studio products, which includes Audition.

Admittedly, audio forensics is a small, niche market away from their core customer base, but if we are lucky, our needs will overlap the needs of their studio customers and a fine product will become even more useful to us. From a forensics point of view, here are the things that I have on my wish list:

• Improve support for working with multi-channel WAV files that are not intended for surround sound, including easy trimming of multiple channels and saving, for starters.
• Speed up loading of large multi-channel files
• Improve the spectrogram interface to allow easy and accurate display and analysis of specific frequencies.
• Include an option to decrease the streamlining (in other words, an "option to allow more options")
  

If you have anything to add to the list, just email me (link found on right side, near the top - don't forget to remove the anti-spam text!) or post a comment.

Computer Audio & Video: Windows Vista changes how audio and video are handled

Howstuffworks has the best summary of Windows Vista as related to audio and video rendering that I've read thus far. The highlights are:

• The graphics and audio drivers will run in user mode instead of kernal mode so that errors with either will not cause 'Blue Screens of Death.'
• Vista supports DirectX 9 but is really built around DirectX 10.
• DirectX previously did not require graphics hardware to support many DirectX capabilities; now, however, only three features are optional.
• Finally, the sound volume coming from each application can be separately controlled.

There is even more interesting information about Vista in the article for those who are interested.