- Details
Audio Library is a client-server system enabling the visually-impaired to access a large database of books over a local network or the Internet. The server enables centralized importing of texts and additional data, sorting and searches based on various keys. It also supports of user authorization based on multi-level passwords.
The client establishes connection with the server, enables database access and download of the required book in a special textual format. The book can then be read out locally, through speech synthesis integrated into the client application. Books can also be converted into audio files, burned onto CDs and listened to on regular CD players..
The entire application provides continuous audible output, and thus the visually impaired do not need a separate screen reader to use it. They can navigate through texts using chapter and paragraph marks, as well as user-defined bookmarks.
Special attention was given to copyright protection. Namely, books are stored in an encrypted form at the client side, and it is not possible to use them without any limitations but only to listen to them. In this way publishers are protected from copyright infringement, and the visually impaired still have access to a multitude of books.
- Details
By using speech technologies, it is relatively easy to create voice portals and provide the disabled with fast and unlimited access to various information allowing them to equally take their part in the community. Voice portals provide them with an insight into the world of science, media and other contents...
Diverse textual contents can be made available over the telephone line by using speech synthesis. On the other hand, speech recognition can be used to navigate through the menu structure of the voice portal. Text contents can be manually entered, taken from database, automatically created based on the contents of a web page etc.
Interactive Voice Response (IVR) systems represent a wide range of applications characterized by the human/computer communication over the telephone. Features and applications of IVR systems can vary depending on the client needs and requests.
- Details
A system for speech synthesis intended particularly for the visually impaired. As it supports Microsoft SAPI5 interface, it can be used in combination with any of the popular screen-reading programs (JAWS, NVDA, Window-Eyes, Dolphin SuperNova...) AnReader has all the functionalities of the AlfaNumTTS system.
AnReader is also intended for persons with other disabilities. People with multiple sclerosis and those with infantile cerebral palsy are often not able to read because reading requires remarkable efforts from them. The speech impaired can use anReader to speak for them. Dyslexic people often have problems with reading, as regards both accuracy and reading speed. These reading problems affect their ability to completely understand written text. All this affects their independence in both work and personal life, which particularly affects children and young people as the developing individuals.
AnReader can be very useful as an educational tool. It gives the possibility to convert e.g. lessons or other textual material into audio files and make it accessible to everyone. Owing to this, anyone can learn (using their mobile phones or MP3 players) even when they otherwise could not (on the road, during some physical activity, etc).
The AlfaNum company keeps improving this anReader, and the latest version can always be purchased on AnReader download page. The software is protected by a HASP device (a hard-lock) or serial number.
- Details
AlfaNum TTS is a system for text-to-speech synthesis with elements of natural intonation, considered to be the best speech synthesizer across the countries of former Yugoslavia. There are versions for Serbian, Croatian and Macedonian languages, with a choice between two speakers (male or female), while built-in elements of intonation contribute significantly to the intelligibility and naturalness of synthesized speech. AlfaNum TTS is one of the basic software components that puts the AlfaNum company ahead of its competition. The features of AlfaNum TTS software are:
- Voice quality similar to human (near perfect)
- The system is able to read texts written without letters with diacritics (š, đ, č, ć, and ž), which is useful for reading e-mails
- The system supports standard XML tags for ensuring correct pre-processing of text specifying intonational events etc.
- The system is able to read many words in foreign languages reasonably correctly (Microsoft Windows, Apple iPhone, Google Chrome...)
- Several interfaces are supported: C++ library, COM, SAPI, MRCP, IP server
- The system supports distribution over multiple computers and load balancing, which enables its application in very demanding environments
- Based on neural networks
- Supports custom voices
- Available on PC and Android platforms
This software component can be purchased separately by anyone who wishes to upgrade their system by adding the speech synthesis feature. However, it can be built into a multitude of our stand-alone products and applications, such as AnReader.
We invite you to test our TTS demo, and read more about practical implementation of TTS systems.
- Details
AlfaNum ASR is a system for the recognition of continuous speech in Serbian and kindred languages. It is one of the basic software components that put the AlfaNum company ahead of its competition. ASR software has the following characteristics:
- Recognition is speaker-independent
- Accuracy is above 99% on a set of 100.000 words
- The system provides information on reliability of recognition of individual words
- The system works fast and reliably and, supports modern multi-core and multiprocessor platforms
- The system is completely software-based and does not require any additional hardware
- Several interfaces are supported: C++ library, COM, SAPI, MRCP, IP server
- The system supports distribution over multiple computers and load balancing, which enables its application in very demanding environments
- Available on PC and Android platforms
ASR software component and can be purchased separately by anyone who wishes to upgrade their system by adding the speech recognition feature. However, it can be built into a multitude of our stand-alone products and applications, such as Word Spotter.
We recommend you to take a look at the AlfaNum Speech Recognition System demo, or read more about practical implementation of ASR systems.
