Silence models in weighted finite-state transducers

نویسنده

Philip N. Garner

چکیده

We investigate the effects of different silence modelling strategies in Weighted Finite-State Transducers for Automatic Speech Recognition. We show that the choice of silence models, and the way they are included in the transducer, can have a significant effect on the size of the resulting transducer; we present a means to prevent particularly large silence overheads. Our conclusions include that context-free silence modelling fits well with transducer based grammars, whereas modelling silence as a monophone and a context has larger overheads.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Incremental Language Models for Speech Recognition Using Finite-state Transducers

In the context of the weighted finite-state transducer approach to speech recognition, we investigate a novel decoding strategy to deal with very large n-gram language models often used in large-vocabulary systems. In particular, we present an alternative to full, static expansion and optimization of the finite-state transducer network. This alternative is useful when the individual knowledge s...

متن کامل

Using context-free grammars for embedded speech recognition with Weighted Finite-State Transducers

In this paper we propose an extension to weighted finite-state transducers in order to enable them to model context-free grammars. Classical finite-state transducers are restricted to modeling regular grammars. However, for some tasks it is necessary to use more general context-free grammars. Even some regular grammar models can be scaled down using context-free rules. The paper extents the tra...

متن کامل

Compilation of Weighted Finite-State Transducers from Decision Trees

We report on a method for compiling decision trees into weighted finite-state transducers. The key assumptions are that the tree predictions specify how to rewrite symbols from an input string, and the decision at each tree node is stateable in terms of regular expressions on the input string. Each leaf node can then be treated as a separate rule where the left and right contexts are constructa...

متن کامل

Chorale Harmonization with Weighted Finite-state Transducers

We approach the task of harmonizing chorales through style imitation by probabilistically modelling the harmony of music pieces in the framework of weighted finite-state transducers (WFSTs), which have been used successfully for probabilistic models in speech and language processing. The framework makes it possible to place domain-specific regular constraints on generated sequences, and to inte...

متن کامل