Abdelkhalek Messaoudi

Arabic Broadcast News Transcription Using a One Million Word Vocalized Vocabulary

Recently it has been shown that modeling short vowels in Arabic can significantly improve performance even when producing a non-vocalized transcript. Since Arabic texts and audio transcripts are almost exclusively non-vocalized, the training methods have to overcome this missing data problem. For the acoustic models the procedure was bootstrapped with manually vocalized data and extended with semi-automatically vocalized data. In order to also capture the vowel information in the language model, a vocalized 4-gram language model trained on the audio transcripts was interpolated with the original 4-gram model trained on the (non-vocalized) written texts. Another challenge of the Arabic language is its large lexical variety. The out-of-vocabulary rate with a 65k word vocabulary is in the range of 4-8% (compared to under 1% for English). To address this problem a vocalized vocabulary containing over 1 million vocalized words, grouped into 200k word classes is used. This reduces the out-of-vocabulary rate to about 2%. The extended vocabulary and vocalized language model trained on the manually annotated data give a 1.2% absolute word error reduction on the DARPA RT04 development data. However, including the automatically vocalized transcripts in the language model reduces performance indicating that automatic vocalization needs to be improved

Automatic Speech-to-Text Transcription in Arabic

The Arabic language presents a number of challenges for speech recognition, arising in part from the significant differences in the spoken and written forms, in particular the conventional form of texts being non-vowelized. Being a highly inflected language, the Arabic language has a very large lexical variety and typically with several possible (generally semantically linked) vowelizations for each written form. This article summarizes research carried out over the last few years on speech-to-text transcription of broadcast data in Arabic. The initial research was oriented toward processing of broadcast news data in Modern Standard Arabic, and has since been extended to address a larger variety of broadcast data, which as a consequence results in the need to also be able to handle dialectal speech. While standard techniques in speech recognition have been shown to apply well to the Arabic language, taking into account language specificities help to significantly improve system performance.

Speech transcription in multiple languages

The paper summarizes recent work underway at LIMSI on speech-to-text transcription in multiple languages. The research has been oriented towards the processing of broadcast audio and conversational speech for information access. Broadcast news transcription systems have been developed for seven languages, and it is planned to address several other languages in the near term. Research on conversational speech has mainly focused on the English language, with some initial work on French, Arabic and Spanish. Automatic processing must take into account the characteristics of the audio data, such as needing to deal with the continuous data stream, specificities of the language and the use of an imperfect word transcription for accessing the information content. Our experience thus far indicates that at todays word error rates, the techniques used in one language can be successfully ported to other languages, and most of the language specificities concern lexical and pronunciation modeling.

Speech Recognition System Combination for Machine Translation

The majority of state-of-the-art speech recognition systems make use of system combination. The combination approaches adopted have traditionally been tuned to minimising word error rates (WERs). In recent years there has been a growing interest in taking the output from speech recognition systems in one language and translating it into another. This paper investigates the use of cross-site combination approaches in terms of both WER and impact on translation performance. In addition, the stages involved in modifying the output from a speech-to-text (STT) system to be suitable for translation are described. Two source languages, Mandarin and Arabic, are recognised and then translated using a phrase-based statistical machine translation system into English. Performance of individual systems and cross-site combination using cross-adaptation and ROVER are given. Results show that the best STT combination scheme in terms of WER is not necessarily the most appropriate when translating speech.

A Divide-and-Conquer Approach for Language Identification Based on Recurrent Neural Networks.

This paper describes the design of an acoustic language recognition system based on BLSTM that can discriminate closely related languages and dialects of the same language. We introduce a Divide-and-Conquer (D&C) method to quickly and successfully train an RNN-based multi-language classifier. Experiments compare this approach to the straightforward training of the same RNN, as well as to two widely used LID techniques: a phonotactic system using DNN acoustic models and an i-vector system. Results are reported on two different data sets: the 14 languages of NIST LRE07 and the 20 closely related languages and dialects of NIST OpenLRE15. In addition to reporting the NIST Cavg metric which served as the primary metric for the LRE07 and OpenLRE15 evaluations, the EER and LER are provided. When used with BLSTM, the D&C training scheme significantly outperformed the classical training method for multi-class RNNs. On the OpenLRE15 data set, this method also outperforms classical LID techniques and combines very well with a phonotactic system.