کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
565369 | 875749 | 2009 | 12 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Efficient codebooks for fast and accurate low resource ASR systems
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
پردازش سیگنال
پیش نمایش صفحه اول مقاله
چکیده انگلیسی
Today, speech interfaces have become widely employed in mobile devices, thus recognition speed and resource consumption are becoming new metrics of Automatic Speech Recognition (ASR) performance.For ASR systems using continuous Hidden Markov Models (HMMs), the computation of the state likelihood is one of the most time consuming parts. In this paper, we propose novel multi-level Gaussian selection techniques to reduce the cost of state likelihood computation. These methods are based on original and efficient codebooks. The proposed algorithms are evaluated within the framework of a large vocabulary continuous speech recognition task.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Speech Communication - Volume 51, Issue 9, September 2009, Pages 732–743
Journal: Speech Communication - Volume 51, Issue 9, September 2009, Pages 732–743
نویسندگان
Leila Zouari, Gérard Chollet,