Digital Signal Processing and Computer Telephony Via Voice Modems Software for Windows

Apollo
$0 - Apollo Software

Apollo started out as a MP3-player. It is recognized by its outstanding MP3 decoding quality, powerful continuous playback support and advanced playlist capabilities. It supports different file formats through so called input plug-ins. Writing an input plug-ins is rather straight forward (see the plug-ins page for more info) and thus Apollo can be easily made to support new audio formats. The player routines provide continuous playback or even a crossfade between tracks on all supported formats and with all output types (standard Wave Out, DirectSound and WAV file output). It is possible to direct the output into a WAV file, thus making it possible, for instance, to decode MP3s for writing them onto a CD. The player routines also provide a realtime 16-band equalizer for all file types.

Currently Apollo ships with two input plug-ins: Apollo MPEG decoder and Apollo WAV decoder. The MPEG decoder is capable of handling both MPEG-1, MPEG-2 and MPEG-2.5 audio layer 2 and 3 files (i.e. MP2- and MP3-files). The decoder is capable of producing 32-bit, 24-bit, 16-bit and 8-bit data. Also Xing and Fraunhofer VBR MP3s are supported. The MPEG decoder is generally thought to be one of the best as far as sound quality is concerned (see FAQ for more information about the quality). The WAV decoder supports RIFF WAV files containing PCM or Microsoft ADPCM coded data. Both plug-ins support Internet streaming.

Apollo also provides support for other type of plug-ins, namely visualization, digital signal processing (DSP) and general purpose plug-ins. Their formats are identical with the corresponding Winamp 2.xx plug-ins. Thus all existing Winamp plug-ins of these three categories should work with Apollo. Also, Winamp input plug-ins that really provide the sound data instead of directly controlling the output device are supported by Apollo.

---

---

Luxand FaceSDK
$2350 - Luxand Development

Detect human faces and recognize facial features in your applications with Luxand FaceSDK.

Digital camera manufacturers spend millions of dollars developing face recognition technologies for their digital cameras. Digital Signal Processors (DSP) combined with face detection algorithms do the job in digital cameras, allowing for better autofocus and proper exposure. These DSPs can only recognize human faces, but don't go any further than that. Modern solutions do not provide facial feature detection, and hence their applications are limited.

Facial feature recognition allows automating common post-processing tasks such as red-eye removal and skin tone adjustment. Users of digital cameras benefit from more precise automatic adjustments and touch-ups that don't require user intervention. Enable face recognition in your software without the need to spend millions of dollars and with no DSP with Luxand FaceSDK!

Luxand FaceSDK employs sophisticated algorithms to detect frontal human faces on digital pictures quickly and reliably. The SDK processes the image, detects human faces, and returns the coordinates of 40 facial feature points including the eyes, eye corners, eyebrows, mouth corners, nose tip, and so on.
Developing morphing, animation or 3D software? Create a perfect 'skin' or a 3D head model automatically! Luxand FaceSDK can select human faces and return pictures that contain the coordinates of facial features, making it easy to match facial features of the photograph with the corresponding features on the 3D head.
Luxand FaceSDK is implemented as a highly compatible Win32 DLL, and supports popular development environments. Microsoft Visual C++ and Borland Delphi users get all necessary header files, making it easy to integrate with new or existing projects.

Create graphical editors or automatic red-eye removal products. Develop solutions for making 3D head models with a single photograph. Morph, animate or transform human faces with Luxand FaceSDK!

---

---

Chorus Producer
$49.9 - Voice Imitation & Recognition Ltd.

Chorus Producer allows an easy way to produce a vocal band from one vocal singer up to 99 different vocal singers and then to save them to one vocal WAV file.
The program performs from one vocal WAV file many different voices by manually setting the gender and adjustment of pitch and vocal tract with high performance and quality, as well as many features like silence tempo delay setting and volume for each track including signal restoration filter. Handling 44.100Sps 16Bits Stereo WAV signal format Pitch and Vocal Tract accurate adjustment for each Singer track Silence Tempo and Negative and positive delay in ms Resolution play any track result and manual adjusting Setting each track to speaker side and volume Signal restoration filter for rebuild and fix the source signal for over amplitude recording up to 30%. Digitally scales for accurate processing and inspection High-accurate low resolution manual adjusting Stereo vocal signal graph

---

AutoSecretary
$150 - Computer telephony via voice modems

Modern business is heavily relied on automatic telephony solutions. Managing customers' calls and providing support using voice lines is one of the most important tasks every business has to accomplish. The technology today offers various solutions, however most of them are very complicated, requiring a dedicated technician to operate the machine-powered service. Moreover, most of them are priced way to high to comply with profitability matter. So, is everything that miserable? Presenting Autosecretary by Eugene Abramov ...
Most of the computer telephony solutions, you may have ran into, require additional hardware for call processing and voice recognition. Autosecretary offers absolutely different approach, utilizing innovative software voice processing technology. It requires only a voice modem and a sound card to bring you full blown computer telephony solution that allows you to put almost insurmountable task of giving the same information over a phone line to hundreds or thousands of customers on the shoulders of a computer system.
Autosecretary is capable of handling incoming and outgoing phone calls based on AI (artificial intelligence) voice processing feature. Whether you run a technical support line that offers different information, basing on user input (both as DFTM tone signals and speech) or a telephone announcement broadcast service, Autosecretary is your choice! It can call your customers on the telephone and give them different sets of voice information depending on what you want to tell this group of customers. Autosecretary is script driven, featuring its own SQL-like script language easy to learn and use so that even a kid could use it.
Autosecretary can operate as a digital answering machine recording all incoming calls and storing them in a database for further re-use. You can record callers' voice messages (the recording time is limited by free HDD space only) and then re-use them when constructing your own phone line broadcasts.

---

Speed Processor
$29.9 - Voice Imitation & Recognition Ltd.

Speed Processor is a software module that allows transformation of vocal and music pitch and speed by manually changing the speed values and voice pitch with high performance and quality. This powerful tool is based on robust algorithms that provides flexible process of vocal file and let the user to save and play the transformed file.High-accuracy efficient mathematic processing with friendly user interface.
- Handling 44.100Sps 16Bits Stereo WAV signal format
- Manually Pitch and Speed adjustment
- Play files in loop for continuous processing
- Digitally scales for accurate process inspection
- High-accurate low resolution manual adjusting
- Internet downloads updates ability
- Stereo vocal signal graph

User Benefits
- Ability to provide special voice speed processing effects
- high-accurate wide-spectrum transforming
- Improving vocal composing for recording studios
- Editing effects for post-productions studios
- Performing high quality vocal transformation and shaping.

---

Vocal Transformation Pro
$49.9 - Voice Imitation & Recognition Ltd.

Vocal Transformation is a software module that allows transformation of vocal signals by manually changing of defined voice pitch and vocal tract values with high performance quality. This powerful tool is based on robust algorithms that provide flexible process of vocal file and let the user to save and play the transformed file.Handling 44.100Sps 16Bits Stereo WAV signal format.Manually Pitch and Vocal Tract adjustment.Add signal Hoarse and Nasality effect
Transforming single voice to a wide multiple voices.Gender setting and converting (male, female & child) for each file. Digitally scales for accurate process inspection. High-accurate manual adjusting using existing audio hardware device. Left-Mouse super functions.Monitoring each working step.Internet downloads updates ability. Multiple real-time task processing ability

---