Unsupervised Acoustic Model Adaptation Based on Ensemble Methods
نویسندگان
چکیده
منابع مشابه
Unsupervised acoustic model adaptation based on phoneme error minimization
In this paper, a new decoding method for unsupervised acoustic model adaptation is presented. In unsupervised adaptation framework, the effectiveness of adaptation process is greatly affected by the mis-recognized labels. Therefore, selection of the adaptation data guided by the confidence measures is effective in unsupervised adaptation. We propose phoneme error minimization framework for exac...
متن کاملmortality forecasting based on lee-carter model
over the past decades a number of approaches have been applied for forecasting mortality. in 1992, a new method for long-run forecast of the level and age pattern of mortality was published by lee and carter. this method was welcomed by many authors so it was extended through a wider class of generalized, parametric and nonlinear model. this model represents one of the most influential recent d...
15 صفحه اولSpeech Data Clustering Based on Phoneme Error Trend for Unsupervised Acoustic Model Adaptation
Unsupervised cluster adaptive training of acoustic models offers promise in improving recognition accuracy, especially for speech recognition systems that store massive sets of speech samples from unknown people. How to classify the variety of acoustic characteristics is an important problem in adaptation sample clustering. We propose a novel speech sample clustering method that focuses on the ...
متن کاملEnsemble Methods for Unsupervised WSD
Combination methods are an effective way of improving system performance. This paper examines the benefits of system combination for unsupervised WSD. We investigate several votingand arbiterbased combination strategies over a diverse pool of unsupervised WSD systems. Our combination methods rely on predominant senses which are derived automatically from raw text. Experiments using the SemCor a...
متن کاملOnline Unsupervised Multilingual Acoustic Model Adaptation for Nonnative Asr
Automatic speech recognition (ASR) is currently one of the main research interests in computer science. Hence, many ASR systems are available in the market. Yet, the performance of speech and language recognition systems is poor on nonnative speech. The challenge for nonnative speech recognition is to maximize the accuracy of a speech recognition system when only a small amount of nonnative dat...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Journal of Selected Topics in Signal Processing
سال: 2010
ISSN: 1932-4553,1941-0484
DOI: 10.1109/jstsp.2010.2076010