کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
563119 875471 2013 11 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Fast unsupervised adaptation based on efficient statistics accumulation using frame independent confidence within monophone states
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر پردازش سیگنال
پیش نمایش صفحه اول مقاله
Fast unsupervised adaptation based on efficient statistics accumulation using frame independent confidence within monophone states
چکیده انگلیسی

This paper proposes a fast unsupervised acoustic model adaptation technique with efficient statistics accumulation for speech recognition. Conventional adaptation techniques accumulate the acoustic statistics based on a forward–backward algorithm or a Viterbi algorithm. Since both algorithms require a state sequence prior to statistic accumulation, the conventional techniques need time to determine the state sequence by transcribing the target speech in advance. Instead of pre-determining the state sequence, the proposed technique reduces the computation time by accumulating the statistics with state confidence within monophone per frame. It also rapidly selects the appropriate gender acoustic model before adaptation, and further increases the accuracy by employing a power term after adaptation. Recognition experiments using spontaneous speech show that the proposed technique reduces computation time by 57.3% while providing the same accuracy as the conventional adaptation technique.


► We propose the efficient accumulation of statistics for unsupervised adaptation.
► Our statistics accumulation does not require us to determine the state sequence.
► We accumulate the statistics using frame independent confidence within monophones.
► We select the gender before adaptation and employ a power term after adaptation.
► Our proposal reduces computation time by 57.3% with no major loss of accuracy.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Computer Speech & Language - Volume 27, Issue 1, January 2013, Pages 369–379
نویسندگان
, , , , , ,