Recent progress in Arabic broadcast news transcription at BBN
نویسندگان
چکیده
The first part of this paper describes the BBN system that participated in the 2004 broadcast news (BN) evaluation for Arabic. The complete system description is given together with experimental results on the 2004 development, and evaluation sets. Previous Arabic speech recognition at BBN used grapheme models due to the lack of short vowel information in the acoustic transcriptions. In the second part of this paper we show how to build a phonetic system. It is demonstrated that switching to phonetic models is capable of reducing the word error rate by up to 14% relative, for different test sets, compared to the traditional grapheme based approach.
منابع مشابه
Japanese broadcast news transcription
In this paper, we describe the on-going development of a Japanese Broadcast News Transcription system at BBN Technologies. This is a collaboration between BBN and NHK to use automatic speech recognition technology to provide live closed caption for NHK’s TV news programs in Japan. We describe what the NHK Broadcast News Corpus comprises and how we adopted transcription technology developed for ...
متن کاملThe BBN Mandarin broadcast news transcription system
In this paper, we present the state-of-the-art BBN Mandarin Broadcast News (BN) transcription system that participated in the EARS Rich Transcription evaluations. As briefly mentioned in the literature before, the BBN 2003 evaluation system achieved 47% relative improvement compared to the baseline, a significant reduction in recognition errors. Since then the system performance has been improv...
متن کاملThe need to create a media block for the convergence of overseas news networks
As a general diplomacy arm of the Islamic Republic of Iran, VoSiMa has extensive activities in international broadcasting of its radio and television programs. These programs are broadcast in different languages, such as English, French, Azeri, Arabic, and ... for regional and transnational audiences. The large volume of the organization's international activities is in the form of news and new...
متن کاملToward realtime transcription of broadcast news
In this paper, we describe our recent work in fast automatic transcription of broadcast news programming from radio and television. Given our state-of-the-art BBN BYBLOS primary system [1] running at 230 times real time (230xRT) we show that eliminating and approximating many computationally expensive components speeds up the system by a factor of more than 20 without significant loss in recogn...
متن کاملThe 1997 Bbn Byblos System Applied to Broadcast News Transcription
In this paper, we describe the BBN Byblos system used for the 1997 DARPA Hub-4 Broadcast News evaluation and discuss numerous improvements made to the system in 1997. We focused our e ort entirely upon the two conditions containing studio-quality uncorrupted speech from native speakers, the so-called F0 (prepared speech) and F1 (spontaneous speech) conditions. In particular, we did not bother t...
متن کامل