Man-Machine Speech Communication: 14th National Conference, NCMMSC 2017, Lianyungang, China

The 14th National Conference on Man-Machine Speech Communication, NCMMSC 2017, held in Lianyungang, China, in October 2017, had 39 submissions and 13 revised full papers. The papers address challenging issues in speech recognition and enhancement, speaker and language recognition, speech synthesis, corpus and phonetic in speech technology, speech generation, speech analyzing and modelling, speech processing of ethnic minorities, speech emotion recognition, and audio signal processing.

Format: Paperback / softback
Length: 143 pages
Publication date: 03 February 2018
Publisher: Springer Verlag, Singapore

The 14th National Conference on Man-Machine Speech Communication (NCMMSC 2017) was held in Lianyungang, China, in October 2017. The conference featured 13 revised full papers, carefully reviewed and selected from 39 submissions. These papers addressed a wide range of topics in speech technology, including challenging issues in speech recognition and enhancement, speaker and language recognition, speech synthesis, corpus and phonetic in speech technology, speech generation, speech analyzing and modelling, speech processing of ethnic minorities, speech emotion recognition, and audio signal processing.

The conference aimed to bring together researchers, practitioners, and industry experts from around the world to discuss the latest advancements and challenges in speech communication. The papers presented at the conference covered a diverse range of topics, reflecting the latest research and developments in the field.

Speech recognition and enhancement: The papers in this category explored various techniques for speech recognition, including deep learning, statistical language models, and hybrid approaches. The challenges of speech recognition in noisy environments, speaker identification, and language adaptation were also discussed.

Speaker and language recognition: The papers in this category focused on developing algorithms for speaker recognition and language identification. The use of voiceprints, speech features, and machine learning techniques was explored to improve the accuracy and reliability of these systems.

Speech synthesis: The papers in this category discussed the development of speech synthesis systems that can produce natural and human-like speech. The use of text-to-speech technology, voice conversion, and speech emotion recognition were explored to enhance the quality of synthesized speech.

Corpus and phonetic in speech technology: The papers in this category explored the use of corpora and phonetic in speech technology. The development of speech databases, the analysis of speech data, and the application of phonetic knowledge to improve speech recognition and synthesis were discussed.

Speech generation: The papers in this category discussed the development of speech generation systems that can generate speech from text or other input sources. The use of deep learning, statistical models, and voice conversion techniques were explored to improve the quality and naturalness of generated speech.

Speech analyzing and modelling: The papers in this category explored the development of speech analysis and modelling algorithms. The use of machine learning, statistical models, and signal processing techniques was explored to improve the accuracy and reliability of speech analysis and modelling systems.

Speech processing of ethnic minorities: The papers in this category focused on the speech processing of ethnic minorities. The challenges of speech recognition and synthesis in minority languages, the development of speech recognition systems for minority languages, and the use of phonetic knowledge to improve speech recognition in minority languages were discussed.

Speech emotion recognition: The papers in this category explored the development of speech emotion recognition systems that can detect and classify the emotions expressed in speech. The use of machine learning, acoustic features, and speech analysis techniques were explored to improve the accuracy and reliability of speech emotion recognition systems.

Audio signal processing: The papers in this category discussed the development of audio signal processing algorithms for speech enhancement, noise reduction, and speech recognition. The use of deep learning, statistical models, and signal processing techniques were explored to improve the performance of audio signal processing systems.

Overall, the 14th National Conference on Man-Machine Speech Communication (NCMMSC 2017) was a successful event that brought together researchers, practitioners, and industry experts from around the world to discuss the latest advancements and challenges in speech communication. The papers presented at the conference covered a wide range of topics and provided valuable insights into the future of speech technology.

Weight: 280g
Dimension: 155 x 234 x 14 (mm)
ISBN-13: 9789811081101
Edition number: 1st ed. 2018