Decision Tree-Based Acoustic Models for Speech Recognition with Improved Smoothness
نویسندگان
چکیده
منابع مشابه
Decision Tree-Based Acoustic Models for Speech Recognition with Improved Smoothness
This article proposes a new acoustic model using decision trees (DTs) as replacements for Gaussian mixture models (GMM) to compute the observation likelihoods for a given hidden Markov model state in a speech recognition system. DTs have a number of advantageous properties, such as that they do not impose restrictions on the number or types of features, and that they automatically perform featu...
متن کاملDecision tree based rate of speech modeling for speech recognition
A real-world speech recognition system encounters several speaking styles and speaking rates and its accuracy depends highly on the speaking rate, i.e., degrades sharply with very fast or very slow speech (including hyperarticulated speech) In this paper, we propose a generic modeling scheme to capture a range of speaking rates from very slow to very fast with the use of decision trees. This ap...
متن کاملCrosslingual speech recognition with multilingual acoustic models based on agglomerative and tree-based triphone clustering
The paper describes our ongoing work on crosslingual speech recognition based on multilingual triphone hidden Markov models. Multilingual acoustic models were built using two different clustering procedures: agglomerative triphone clustering and tree-based triphone clustering. The agglomerative clustering procedure is based on measuring the similarity of triphones on a phoneme level where the m...
متن کاملClass-triphone Acoustic Modeling Based on Decision Tree for Mandarin Continuous Speech Recognition
Decision tree based acoustic modeling has increasingly become popular for modeling speech spectral variations in continuous speech. In this paper, class-triphone acoustic models based on the decision tree are investigated for mandarin speakerindependent continuous speech recognition. Three main questions are discussed: how to select base phone models, how to generate the question set based on l...
متن کاملImproved Acoustic Modeling for Continuous Speech Recognition
We report on some recent improvements to an HMMbased, continuous speech recognition system which is being developed at AT&T Bell Laboratories. These advances, which include the incorporation of inter-word, context-dependent units and an improved feature analysis, lead to a recognition system which achieves better than 95% word accuracy for speaker independent recognition of the 1000-word, DARPA...
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: IEICE Transactions on Information and Systems
سال: 2011
ISSN: 0916-8532,1745-1361
DOI: 10.1587/transinf.e94.d.2250