Selection of Multi-Word Expressions from Web N-gram Corpus for Speech Recognition
نویسندگان
چکیده
This paper proposes a method for constructing a statistical language model with multi word expressions (MWEs) selected from Google Japanese Web N-gram. MWEs are concatenated words that consist of idiomatic expressions or long-length morpheme sequences used frequently. In this paper a method for selecting the effective MWEs that improve the language model based on co-occurrence probabilities of the MWEs is reported. The speech recognition experiments for the Corpus for Spontaneous Japanese are conducted to investigate the effectiveness of the MWE language model. The experimental results show that the proposed method can improve the recognition performance.
منابع مشابه
New language models using phrase structures extracted from parse trees
This paper proposes a new speech recognition scheme using three linguistic constraints. Multi-class composite bigram models [1] are used in the first and second passes to reflect word-neighboring characteristics as an extension of conventional word n-gram models. Trigram models with constituent boundary markers and word pattern models are both used in the third pass to utilize phrasal constrain...
متن کاملAllophone-based acoustic modeling for Persian phoneme recognition
Phoneme recognition is one of the fundamental phases of automatic speech recognition. Coarticulation which refers to the integration of sounds, is one of the important obstacles in phoneme recognition. In other words, each phone is influenced and changed by the characteristics of its neighbor phones, and coarticulation is responsible for most of these changes. The idea of modeling the effects o...
متن کاملImproving trigram language modeling with the World Wide Web
We propose a novel method for using the World Wide Web to acquire trigram estimates for statistical language modeling. We submit an N-gram as a phrase query to web search engines. The search engines return the number of web pages containing the phrase, from which the N-gram count is estimated. The N-gram counts are then used to form web-based trigram probability estimates. We discuss the proper...
متن کاملStatistical Language Modeling with pro for Continuous Speech
A new statistical language modeling was proposed where word n-gram was counted separately for the cases crossing and not crossing accent phrase boundaries. Since such counting requires a large speech corpus, which hardly can be prepared, part-of-speech (POS) n-gram was first counted for a small-sized speech corpus for the two cases instead, and then the result is applied to word n-gram counts o...
متن کاملAutomatic n-gram language model creation from web resources
This paper describes an automatic building of N-gram language models from Web texts for large vocabulary continuous speech recognition. Although a huge amount of well-formed texts are needed to train a model, collecting and organizing such text corpus for every task by hand needs a great labor. We need the language model to update frequently to cover the current topics. To deal with this proble...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2013