arabic, anism1a.gif (1984 bytes)arabic software solutions, anism1b1.gif (3409 bytes)arabic, anism1a2.gif (1972 bytes)

Arabic Software  Desktop Publishing  Translation   OCR  ASR  TTS  MultimediA


ASR | Categorization | Correction | Diacritization | DMS/ArabDox | Ibsar Reading Machine | IDRISI Search
Johaina | Keyword Extraction | KMS | MMMP | MT | NLP | OCR |
Services  | SET | Speech | Summarization | TTS





Sakhr Software Launches Sakhr's Arabic ASR 4.0
 Automatic Speech Recognition Engine

Sakhr Software, the pioneering Arabic IT Company and supplier of speech recognition and text to speech technologies and business solutions, announced the availability of its engine Sakhr's ASR 4.0 software package. The version 4.0 of the ASR is the successor of Sakhr's ASR 3.0, containing new functionalities to ease application development and integration, increase accuracy and improve application usability. The ASR engine enables IVR systems to understand people's natural Arabic speech through spoken words in different Arabic accents. Developed for telephony speech applications, the recognition engine provides speech recognition and understanding for human-like telephony services.

With ASR 4.0, developers can create robust and easy-to-use application interfaces designed to increase customer self-service, shorten transaction completion time and boost customer satisfaction levels. The ASR is designed to enable highly accurate, scalable, and easy to deploy voice solutions ranging from directory assistance, banking solutions, auto-attendant systems, product ordering, solutions for visually impaired and customer care to industry specific applications including airline reservations, brokerage, and many more.

Sakhr's ASR software is a speaker-independent, open, standards-based recognition engine optimized for scalability, accuracy, and performance particularly for wireless environments and hands-free operation. The engine delivers unparalleled accuracy, often exceeding 95% in both wireless and landline deployments and exceptionally in noisy environments. It allows natural human-like dialogues through its robust grammar based barge-in feature. The latest ASR engine release builds on the advanced capabilities of the version 3.0 to provide memory and CPU savings and support for application vocabularies containing millions of entries.

"This version of the ASR is packaged with latest features required by the market and the highest accuracy ever achieved", said Jihad Salman, product manager for speech technologies at Sakhr. "Sakhr's ASR 4.0 allows the developers to easily speech-enable their telephony applications for the Arabic market and with its high accuracy enhances the quality of service while increasing the customers' satisfaction".

The engine 4.0 comes with a completely revised toolkit, which comprises a complete set of new tools and enhanced support of the entire application development process via a consistent and ergonomic workflow scheme. The new toolkit provides more graphical user interface (GUI) tools for application design, as well as for application tuning and evaluation. It incorporates tools for easily training with open grammars and for creating and transcribing speech corpora.

The TeleMedia 900 Audiotel Case

TeleMedia is one of 2 companies in Egypt that provide AudioTel applications i.e. prepaid phone services and contexts that use 900 numbers based on closed publicity activity in the television.

The Situation
Based on Interactive Voice Response (IVR) systems used in Computer Telephony (CT), TeleMedia provides 900 numbers with special tariffs in cooperation with Egypt Telecom. Users have to follow recorded instructions and reply by pressing number keypads to select an answer or respond to instructions. Recording message isn't practical and costs a lot with dynamic data and the use of DTMF instead of natural speech is tedious for the speakers in large menus.

The Challenge
The challenge was to deliver Arabic speech engines compatible with TeleMedia infrastructure, and able to automate the tedious and costly process of recording different prompts for various applications. Moreover the need to start a new human recording if the data is changed limits the scope of the application that the original system can handle. For example it won't be able to provide dynamic listings of names or broadcasting of the latest news from the web.

On the other side, handling the caller requests in natural speech instead of DTMF is really challenging due to the variability of possible utterance that people can say in different ways even if the choices were limited. Moreover the probability of providing different speech than the expected and noise interference may limit the accuracy of any speech recognition system.

Finally this automation by Sakhr technologies should manage with the huge number of calls that TeleMedia receives specially in the peak hours of TV when publicity campaigns encourage people to call for a contest or service. The design should be flexible enough to toggle between different applications based on the online load and therefore route the service accordingly.

The Solution
We proposed a complete solution that solves all customers concerns and fulfill all the requirements including:
  1. Automatic Speech Recognition (ASR): this engine was:
    • Based on a complete SDK that enables the developer to build any context easily.
    • Flexible enough to handle noise or additional utterance using keyword spotting.
    • Able to handle concurrently up to 50 channels.
    • Designed to manage continuous speech efficiently.
  1. Text To Speech (TTS): Major dynamic recordings now can be substituted by the Arabic TTS that handles any un-Diacritized Arabic text efficiently, thanks to Sakhr's automatic Diacritizer, in both intelligible and natural male or female voices.
  2. Load Balancing: TeleMedia and Sakhr worked jointly to cover:
    • Concurrent service covering online callers with optimized load distribution of resources
    • Offline services generating TTS waves to be used by different requests latter.

The Results
The solution brought immense functionality and benefits on the two fronts: TTS used in dynamic prompt messages and users efficient ASR. The implementation of the complete solution satisfied TeleMedia requirements, with their actual heavy calls load with an accuracy of 95% in Automatic Speech Recognition and very high degree of intelligibility and naturalness in Text To Speech.

Please contact George N. Hallak
for more info about Sakhr Enterprise Solutions pricing models.

ASR | Categorization | Correction | Diacritization | DMS/ArabDox | Ibsar Reading Machine | IDRISI Search
Johaina | Keyword Extraction | KMS | MMMP | MT | NLP | OCR |
Services  | SET | Speech | Summarization | TTS



|| Home Page || AramediA Contact Info || Adobe Middle East (ME) || Arabic Fonts || Arabic Language Tutors || All Languages Tutors ||
|| Arabic NewsStand
|| Arabic Resources || American Sign Language (ASL) || Arabic Calligraphy || Children || Desktop Publishing DTP ||
 || Dictionaries of the World || Digital Marvel Comics || Educational Programs || Games for All Ages || Islamic Software ||
Microsoft Arabic Software ||
||
Multilingual Keyboards & Stickers || New Products || OCR || Machine Translation || Sakhr Enterprise Solutions || Search Engines || Software Solutions ||
||
Universal Word || World Resources || Word Processors || The AramediA Sales Policy || Site Map || Software Search || aramediaStore.com ||
Amazon.com ||

AramediA

Arabic Machine Translation
Enterprise and Standalone

Join Our Newsletter

37 Adams Street, Braintree, MA 02184-1906
United States of America (USA)
Tel 1-781-849-0021 Fax 1-781-849-2922

 

animail2.gif (5769 bytes)

We Ship All Around the Globe

Copyright 1995 - 2014 - GnhBos Incorporated dba AramediA. All rights reserved.