Automatic rule-based generation of word pronunciation networks
نویسندگان
چکیده
In this paper a method for generating word pronunciation networks for speech recognition is proposed. The networks incorporate different acceptable pronunciation variants for each word. These variants are determined by applying pronunciation rules to the standard pronunciation of the words. Instead of a manual search, an automatic learning procedure is used to compose a sensible set of rules. The learning algorithm compairs the standard pronunciation of each utterance in a training corpus with its auditory transcription (i.e. ‘how should it be pronounced’ versus ‘how was it actually pronounced’). It is shown that the latter transcription can be constructed with the assistance of a speech recognizer. Experimental results on a Dutch database and on TIMIT demonstrate that the pronunciation networks reduce the word error rate significantly.
منابع مشابه
Pronunciation modeling in hungarian number recognition
In Hungarian, as more or less in many other languages, a large percent of words and phrases can be pronounced in several, different, but correct ways. Introducing pronunciation alternatives for individual vocabulary elements may improve the efficiency of the recognition. But in connected word recognition tasks the modeling of inter-word phonetic changes has a greater significance. In this paper...
متن کاملAutomatic generation and pruning of phonetic mispronunciations to support computer-aided pronunciation training
This paper presents a mispronunciation detection system which uses automatic speech recognition to support computer-aided pronunciation training (CAPT). Our methodology extends a model pronunciation lexicon with possible phonetic mispronunciations that may appear in learners’ speech. Generation of these pronunciation variants was previously achieved by means of phone-tophone mapping rules deriv...
متن کاملGeneration of Word Pronunciation Networks from Automatically Learned Inter-word Coarticulation Rules
| In this paper a method for learning inter-word coarticulation rules from a training set is proposed. The algorithm is based on a comparison of the standard transcription (i.e. `how should it be pronounced') of each utterance with its auditory transcription (i.e. `what was actually pro-nounced'). It is shown that the latter transcriptions can be obtained without human intervention: the speech ...
متن کاملAutomatic Pronunciation Generation by Utilizing a Semi-Supervised Deep Neural Networks
Phonemic or phonetic sub-word units are the most commonly used atomic elements to represent speech signals in modern ASRs. However they are not the optimal choice due to several reasons such as: large amount of effort required to handcraft a pronunciation dictionary, pronunciation variations, human mistakes and under-resourced dialects and languages. Here, we propose a data-driven pronunciation...
متن کاملRule-based Word Pronunciation Networks Generation for Mandarin Speech Recognition
Modeling pronunciation variation in spontaneous speech is very important for improving the recognition accuracy. One limitation of current recognition systems is their dictionaries for recognition only contain one standard pronunciation for each entry, so that the amount of variability that can be modeled is very limited. In this paper, we proposed to generate pronunciation networks based on ru...
متن کامل