Поиск по каталогу |
(строгое соответствие)
|
- Профессиональная
- Научно-популярная
- Художественная
- Публицистика
- Детская
- Искусство
- Хобби, семья, дом
- Спорт
- Путеводители
- Блокноты, тетради, открытки
Automatic Speaker Recognition using Phase based Features. Developing FM based Automatic Speaker Recognition System to Complement Conventional Systems
В наличии
Местонахождение: Алматы | Состояние экземпляра: новый |
Бумажная
версия
версия
Автор: Tharmarajah Thiruvaran,Eliathamby Ambikairajah and Julien Epps
ISBN: 9783639708141
Год издания: 2014
Формат книги: 60×90/16 (145×215 мм)
Количество страниц: 192
Издательство: Scholars' Press
Цена: 47257 тг
Положить в корзину
Позиции в рубрикаторе
Отрасли экономики:Код товара: 138543
Способы доставки в город Алматы * комплектация (срок до отгрузки) не более 2 рабочих дней |
Самовывоз из города Алматы (пункты самовывоза партнёра CDEK) |
Курьерская доставка CDEK из города Москва |
Доставка Почтой России из города Москва |
Аннотация: A theory has been developed to show that the FM component can be extracted using second-order all pole modelling, and a technique for extracting FM features using this model is proposed, to produce very smooth, slowly varying FM features that are effective for speaker recognition. This is evaluated on NIST 2008 international speaker recognition evaluation. Optimum Frequency band allocation specifically to capture speaker specific information is studied in terms of the number of sub-bands and spacing of center frequencies, and two new frequency band re-allocations are proposed for FM based speaker recognition. Furthermore, FM feature is successfully utilized for automatic forensic speaker recognition, which is implemented based on the likelihood ratio framework with two stage modelling and calibration, and shown to behave in a complementary manner to amplitude information.
Ключевые слова: signal processing, pattern recognition, Automatic Speaker Recognition, Forensic, Frequency Modulation
Похожие издания
Отрасли экономики: Приборостроение -> Производство электронных компонентов Nirupam Shome Automatic Speaker Recognition in Diverse Data Condition. A System Based on Signal Processing and Deep Learning Techniques. 1905 г., 208 стр., мягкий переплет Speaker recognition is the process of identifying and verifying a speaker’s voiceprints from several voices. The main objective of speaker recognition is to create a system that is capable of verifying a person’s voice and can also be proficient in identifying a person from his/her voice. This book discusses the challenges of the... | 47825 тг |