Speechmatics Partners with QCRI for Arabic Speech-to-Text Transcription
U.K. firm Speechmatics this week announced plans to use the Qatar Computing Research Institute's Advanced Transcription System to take Arabic speech-to-text services to its global customers.
Speechmatics will use QCRI's Advanced Transcription System to transcribe Arabic broadcasts and audio files into text and subtitles. The system can transcribe modern standard Arabic as well as four major Arabic dialects: Egyptian, Levantine, North African and Gulf Arabic.
"This is not just a technology transfer. It is much bigger. It will allow information sharing in Arabic around the world," QCRI's executive director, Ahmed Elmagarmid, said in a statement.
Speechmatics' chief scientific officer, Tony Robinson, said the development, which used the company's Auto-Auto framework, would ensure Arabic-based content was "more discoverable and easily consumed."
"Speechmatics will help QCRI expand their reach to a broad range of industries and geographies with market-leading speech-to-text services based on the latest research in machine learning and artificial intelligence," he added.
QCRI Arabic Language Technologies principal engineer Ahmed Ali, who has been leading the speech team, said deep neural network (DNN) and recurrent neural network (RNN) architecture were used in QATS' development.
"We used more than 2,000 hours of Arabic speech to develop and train QATS, in addition to a large archive of the Web 2.0 content," he said in a statement.
Arabic broadcaster Al Jazeera Media Network has been using versions of QATS to transcribe its daily Arabic news reports for almost two years.