August 10, 2010 06:45 ET

Bridging the Language Gap: AppTek Announces Major Enhancement of Automated Speech Recognition Telephony Engine for Spanish

AppTek's PlainSpeech™ Telephony Product Underwent Further Development to Be a More Capable Speaker-Independent System for Many Dialects of Latin American Spanish

MCLEAN, VA--(Marketwire - August 10, 2010) -  AppTek, a leader in human language technology (HLT), announced the availability of its automated speech recognition (ASR) engine for Spanish. The enhanced ASR engine also processes several other key languages such as Arabic, Farsi, Urdu, and Chinese and is compatible for use with machine translation, providing a complete solution for commercial customers and to the U.S. Government through AppTek's GSA schedule without integration costs or complex development. 

The PlainSpeech™ Spanish telephony engine is a unique offering in the language technologies market because it is specifically engineered for the challenging content of unscripted natural language, dialect, slang, noise and other aspects of non-broadcast environments. AppTek's PlainSpeech™ telephony engine is unlike AppTek's broadcast audio version in that it is designed for different quality levels and also the challenges posed by unpredictable speech that is neither edited, rehearsed, or uniform.

Deployed for use in several commercial and government applications, AppTek's ASR technology has a proven track record of providing industry leading accuracy and speed. AppTek's ASR technology seamlessly integrates with AppTek's hybrid MT software for the most accurate telephony transcription and translation, and can easily be expanded with new commands to adapt to changing needs and demands on domain specific vocabulary fields.

"The benefits of the enhanced ASR engine go beyond traditional uses, as we are able to provide customers the industry's first solution to employ Spanish transcription and translation in one platform, which can be utilized for many leading-edge machine translation and multilingual information retrieval projects, including media monitoring where it adjusts to changes in dialect and language in real-time to improve speed and accuracy," said Hassan Sawaf, Chief Scientist at AppTek.

For more information on the enhanced ASR engine or any of AppTek's other leading human language technology products, please visit: www.apptek.com. 

ABOUT APPTEK

AppTek, headquartered in McLean, Virginia, is a developer of human language technology products with a complete suite for text and speech (voice) processing and recognition. The company also leads major research and development efforts to further the advancement in the field of developing better methods and technologies in the field of HLT. AppTek's product offerings include machine translation (MT) and automatic speech recognition (ASR) for a growing list of more than 23 languages; multilingual information retrieval with query and topic search capabilities; name-finding applications; and integrated suites providing ASR and MT in media monitoring of broadcast and telephony speech as well as handheld and wearable speech-to-speech translation devices. The company has language professionals and computer scientists in offices around the world.