Hierarchical Neural Network Structures for Phoneme Recognitio
نام عام مواد
[Book]
نام نخستين پديدآور
/ by Daniel Vasquez, Rainer Gruhn, Wolfgang Minker
وضعیت نشر و پخش و غیره
محل نشرو پخش و غیره
Berlin, Heidelberg
نام ناشر، پخش کننده و غيره
: Springer Berlin Heidelberg :Imprint: Springer,
تاریخ نشرو بخش و غیره
, 2013.
مشخصات ظاهری
نام خاص و کميت اثر
XVIII, 133 p. 49 illus., online resource.
فروست
عنوان فروست
(Signals and Communication Technology,1860-4862)
یادداشتهای مربوط به نشر، بخش و غیره
متن يادداشت
Electronic
یادداشتهای مربوط به مندرجات
متن يادداشت
whilst keeping the system accuracy comparable to the baseline hierarchical approach.
متن يادداشت
In this book, hierarchical structures based on neural networks are investigated for automatic speech recognition. These structures are evaluated on the phoneme recognition task where a Hybrid Hidden Markov Model/Artificial Neural Network paradigm is used. The baseline hierarchical scheme consists of two levels each which is based on a Multilayered Perceptron. Additionally, the output of the first level serves as a second level input. The computational speed of the phoneme recognizer can be substantially increased by removing redundant information still contained at the first level output. Several techniques based on temporal and phonetic criteria have been investigated to remove this redundant information. The computational time could be reduced by 57
متن يادداشت
Background in Speech Recognition -- Phoneme Recognition Task -- Hierarchical Approach and Downsampling Schemes -- Extending the Hierarchical Scheme: Inter and Intra Phonetic Information -- Theoretical framework for phoneme recognition analysis.
فروست (داده ارتباطی)
عنوان
Signals and Communication Technology,1860-4862
موضوع (اسم عام یاعبارت اسمی عام)
موضوع مستند نشده
Engineering
موضوع مستند نشده
Computer science
موضوع مستند نشده
Translators (Computer programs)
موضوع مستند نشده
Electronic books
رده بندی کنگره
شماره رده
E-BOOK
نام شخص به منزله سر شناسه - (مسئولیت معنوی درجه اول )