Morphological decomposition in Arabic ASR systems

In recent years, the use of morphological decomposition strategies for Arabic Automatic Speech Recognition (ASR) has become increasingly popular. Systems trained on morphologically decomposed data are often used in combination with standard word-based approaches, and they have been found to yield consistent performance improvements. The present article contributes to this ongoing research endeavour by exploring the use of the 'Morphological Analysis and Disambiguation for Arabic' (MADA) tools for this purpose. System integration issues concerning language modelling and dictionary construction, as well as the estimation of pronunciation probabilities, are discussed. In particular, a novel solution for morpheme-to-word conversion is presented which makes use of an N-gram Statistical Machine Translation (SMT) approach. System performance is investigated within a multi-pass adaptation/combination framework. All the systems described in this paper are evaluated on an Arabic large vocabulary speech recognition task which includes both Broadcast News and Broadcast Conversation test data. It is shown that the use of MADA-based systems, in combination with word-based systems, can reduce the Word Error Rates by up to 8.1 relative. © 2012 Elsevier Ltd. All rights reserved.

Continuous asr for flexible incremental dialogue

Spoken dialogue systems provide a convenient way for users to interact with a machine using only speech. However, they often rely on a rigid turn taking regime in which a voice activity detection (VAD) module is used to determine when the user is speaking and decide when is an appropriate time for the system to respond. This paper investigates replacing the VAD and discrete utterance recogniser of a conventional turn-taking system with a continuously operating recogniser that is always listening, and using the recogniser 1-best path to guide turn taking. In this way, a flexible framework for incremental dialogue management is possible. Experimental results show that it is possible to remove the VAD component and successfully use the recogniser best path to identify user speech, with more robustness to noise, potentially smaller latency times, and a reduction in overall recognition error rate compared to using the conventional approach. © 2013 IEEE.

ASR emotional speech: Clarifying the issues and enhancing performance

There are multiple reasons to expect that recognising the verbal content of emotional speech will be a difficult problem, and recognition rates reported in the literature are in fact low. Including information about prosody improves recognition rate for emotions simulated by actors, but its relevance to the freer patterns of spontaneous speech is unproven. This paper shows that recognition rate for spontaneous emotionally coloured speech can be improved by using a language model based on increased representation of emotional utterances. The models are derived by adapting an already existing corpus, the British National Corpus (BNC). An emotional lexicon is used to identify emotionally coloured words, and sentences containing these words are recombined with the BNC to form a corpus with a raised proportion of emotional material. Using a language model based on that technique improves recognition rate by about 20%. (c) 2005 Elsevier Ltd. All rights reserved.

Industrial ecology applied to ELV management. Material and energy recovery from ASR

This PhD thesis reports on car fluff management, recycling and recovery. Car fluff is the residual waste produced by car recycling operations, particularly from hulk shredding. Car fluff is known also as Automotive Shredder Residue (ASR) and it is made of plastics, rubbers, textiles, metals and other materials, and it is very heterogeneous both in its composition and in its particle size. In fact, fines may amount to about 50%, making difficult to sort out recyclable materials or exploit ASR heat value by energy recovery. This 3 years long study started with the definition of the Italian End-of-Life Vehicles (ELVs) recycling state of the art. A national recycling trial revealed Italian recycling rate to be around 81% in 2008, while European Community recycling target are set to 85% by 2015. Consequently, according to Industrial Ecology framework, a life cycle assessment (LCA) has been conducted revealing that sorting and recycling polymers and metals contained in car fluff, followed by recovering residual energy, is the route which has the best environmental perspective. This results led the second year investigation that involved pyrolysis trials on pretreated ASR fractions aimed at investigating which processes could be suitable for an industrial scale ASR treatment plant. Sieving followed by floatation reported good result in thermochemical conversion of polymers with polyolefins giving excellent conversion rate. This factor triggered ecodesign considerations. Ecodesign, together with LCA, is one of the Industrial Ecology pillars and it consists of design for recycling and design for disassembly, both aimed at the improvement of car components dismantling speed and the substitution of non recyclable material. Finally, during the last year, innovative plants and technologies for metals recovery from car fluff have been visited and tested worldwide in order to design a new car fluff treatment plant aimed at ASR energy and material recovery.

Kitāb al-Mukhtār fī kashf al-asrār

li-Zayn al-Dīn ʻAbd al-Raḥīm ibn ʻUmar al-Dimashqī al-maʻrūf bi-al-Jawbarī.

Kitāb Bahjat al-asrār wa-maʻdan al-anwār fī baʻḍ manāqib al-quṭb al-Rabbānī wa-al-ghawth al-Ṣamadānī wa-al-baḥr al-zākhir al-nūrānī ṣāḥib al-maqām al-ʻalī Muḥyī al-Dīn Abī Muḥammad ʻAbd al-Qādir al-Jīlī

taʼlīf Nūr al-Dīn Abī al-Ḥasan ʻAlī ibn Yūsuf Abī Faḍl al-Shaṭnūbī. Wa-bi-hāmishihi Kitāb Riyāḍ al-basātīn fī akhbār al-Shaykh ʻAbd al-Qādir al-Jīlī Muḥyī al-Dīn taʼlīf Muḥammad al-Amīn al-Kīlānī al-Tūnisī.

Kitāb al-Anwār wa-al-asrār al-mushīr ilá ʻilm al-taksīr : manuscript, undated

بسم الله الرحمن الرحيم وبه نستعين والحمد لله المتعال الكريم ... :Incipit

Tarih-i medeniyet; asr-ǐ hazǐr.

Translation into Turkish, by Ahmed Refīq, of his Histoire de la civilisation dans l'antiquité, Histoire de la civilisation au moyen âge et dans les temps modernes, and Histoire de la civilisation contemporaine.

Natāʾij al-afkār ʻalá al-matn al-musammá bi-Iẓhār al-asrār [microform].

Colophon title.

Lawāmiʻ al-asrār fī Sharḥ Maṭāliʻ al-anwār [microform]

Followed by al-Sayyid ʻalá Sharḥ al-Maṭāliʻ.