This book presents recent advances in NLP and speech technology, a topic attracting increasing interest in a variety of fields through its myriad applications, such as the demand for speech guided touchless technology during the Covid-19 pandemic. The authors present results of recent experimental research that provides contributions and solutions to different issues related to speech technology and speech in industry. Technologies include natural language processing, automatic speech recognition (for under-resourced dialects) and speech synthesis that are useful for applications such as intelligent virtual assistants, among others. Applications cover areas such as sentiment analysis and opinion mining, Arabic named entity recognition, and language modelling. This book is relevant for anyone interested in the latest in language and speech technology.

Presents recent works and experimental research and applications on Natural Language and Speech Processing Includes chapters on speech technology not only for resourced languages For under-resourced languages and dialects

Autorentext

Dr. Mourad Abbas is research director at High Council of Arabic. He taught courses in different schools and universities: signal processing, radio-engineering, operating systems. His research interests include the major issues related to natural language processing, in particular to Arabic language and its dialects. He is interested in Machine translation, Speech recognition, Language identification, Natural Language Understanding, Under-resourced Languages and more other topics.  Dr. Abbas published more than sixty papers, and co-edited proceedings of conferences and workshops (ICNLSP, NSURL) in Elsevier, ACL Anthology, IEEExplore. He reviewed for many journals as: Language Resources and Evaluation, Digital Signal Processing, Engineering Applications of Artificial Intelligence, and conferences as ICASSP, Interspeech, Coling, NAACL-HLT, etc. He founded the International Conference on Natural Language and Speech Processing, in 2015. ****

Inhalt

Chapter 1. ITAcotron 2: the Power of Transfer Learning in Expressive TTS Synthesis.- Chapter 2. Improving Automatic Speech Recognition for Non-Native English with Transfer Learning and Language Model Decoding.- Chapter 3. Kabyle ASR Phonological Error and Network Analysis.- Chapter 4. ALP: an Arabic Linguistic Pipeline.- Chapter 5. Arabic Anaphora Resolution System using New Features: Pronominal and Verbal cases.- Chapter 6. A Commonsense-enhanced Document-Grounded Conversational Agent: A Case Study on Task-based Dialogue.- Chapter 7. BloomQDE: Leveraging Bloom's Taxonomy for Question Difficulty Estimation.- Chapter 8. A Comparative Study on Language Models for Dravidian Languages.- Chapter 9. Arabic Named Entity Recognition with a CRF model based on Transformer Architecture.- Chapter 10. Static Fuzzy Bag-of-Words: Exploring Static Universe Matrices for Sentence Embeddings.