کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
566392 | 875977 | 2006 | 19 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Lattice segmentation and minimum Bayes risk discriminative training for large vocabulary continuous speech recognition
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
پردازش سیگنال
پیش نمایش صفحه اول مقاله
چکیده انگلیسی
Lattice segmentation techniques developed for Minimum Bayes Risk decoding in large vocabulary speech recognition tasks are used to compute the statistics needed for discriminative training algorithms that estimate HMM parameters so as to reduce the overall risk over the training data. New estimation procedures are developed and evaluated for both small and large vocabulary recognition tasks, and additive performance improvements are shown relative to maximum mutual information estimation. These relative gains are explained through a detailed analysis of individual word recognition errors.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Speech Communication - Volume 48, Issue 2, February 2006, Pages 142–160
Journal: Speech Communication - Volume 48, Issue 2, February 2006, Pages 142–160
نویسندگان
Vlasios Doumpiotis, William Byrne,