Verification of phonological rules recognitio
ثبت نشده
چکیده
I introduce a way of verifying phonological processes on the basis of phonetic substances obtained by automatic speech recognition. The acoustic characteristics of phone-like units are modelled using automatic speech recognition techniques. This phone recogniser is run on the data tokens whose segmental structure matches with the context of target processes to be verified. Examining output strings of the recognition reveals whether the rule has been applied. Risk of erroneous recognition is alleviated as the final judgment is based on processing of multiple data tokens in a large spontaneous database.
منابع مشابه
A Natural Language Correction Model for Continuous Speech Recognition
We have developed a method of improving and controlling the accuracy of automated continuous speech recognition through linguistic postprocessing. In this approach, an output from a speech recognitio n system is passed to a trainable Correction Box module which attempts to locate and repair any transcription errors. The Correction Box consists of a text alignment program, a correction-rule gene...
متن کاملRussian Loanword Adaptation in Persian; Optimal Approach
In this paper we analyzed some of the phonological rules of Russian loanword adaptation in Persian, on the view of Optimal Theory (OT) (Prince and Smolensky, 1993, 2003). It is the first study of phonological process on Russian loanwords adaptation in Persian. By gathering about 50 current Russian loanwords, we selected some of them to analyze. We found out that vowel insertion, vowel prothesis...
متن کاملEthnography of Reading
Ethnography of Reading Written Language A Short History of Reading Research Tunnel Vision and Knowledge Visual Information and Redundancy Orthographic Structure Measures of Orthographic Structure Perceptual versus Memory Contributions Reicher Paradigm Words versus Rules Phonological Mediation Experimental Tests Theories of Word Recognition Logogen Model Cohort Model Activation-Verification Mode...
متن کاملAutomatic Detection and Verification of Dutch Phonological Rules
In this paper, we propose two methods for automatically obtaining hypotheses about pronunciation variation. To this end, we used two different approaches in which we employed a continuous speech recognizer to derive this information from the speech signal. For the first method, the output of a phone recognition was compared to a reference transcription in order obtain hypotheses about pronuncia...
متن کاملEffects of the phonological relevance in speaker verification
This paper analyze the effects of phonological relevance between the training and test utterances in speaker verification, and presents experimental evaluations using short test utterances in 3, 5 and 10 seconds. We quantify the phonological relevance as the occurrence ratio of the subword units of the test utterance in the training utterance. It is found that a higher phonological relevance ca...
متن کامل