Automatic Generation of Phon for Large Speech C
نویسندگان
چکیده
We describe a method for the automatic production of phonetic transcriptions in large speech corpora. First, we focus on the application of different techniques for the generation of pronunciation variants. Then, we explain the application of a speech recognition system for selecting the acoustically best matching phonetic transcription. The system is evaluated on different test sets selected from the Spoken Dutch Corpus, ranging from read-aloud text to spontaneous speech, and achieves promising first results.
منابع مشابه
Combined Systems for Automatic Phonetic Transcription of Proper Nouns
Large vocabulary automatic speech recognition (ASR) technologies perform well in known, controlled contexts. However recognition of proper nouns is commonly considered as a difficult task. Accurate phonetic transcription of a proper noun is difficult to obtain, although it can be one of the most important resources for a recognition system. In this article, we propose methods of automatic phone...
متن کاملAutomatic generation of phonological variations
A recognition system must include structures which accoupt f?r ~he di~feren~ aspects of. possible phonological vanab1hty m the mcommg speech s1gnal. To aid in dealing with variability at the phonological level, a grapheme-toseveral-phoneme strings module, V ARIONO, has been developed at LIMSI. Tests of this system showed the necess1ty of creating a hierarchical structure to order phon<?lo~ica~ ...
متن کاملA Database for Automatic Persian Speech Emotion Recognition: Collection, Processing and Evaluation
Abstract Recent developments in robotics automation have motivated researchers to improve the efficiency of interactive systems by making a natural man-machine interaction. Since speech is the most popular method of communication, recognizing human emotions from speech signal becomes a challenging research topic known as Speech Emotion Recognition (SER). In this study, we propose a Persian em...
متن کاملIntroducing Phon: A Software Solution for the Study of Phonological Acquisition.
In this paper, we introduce a new software program, Phon, which aims at providing unprecedented functionality for the elaboration, analysis and sharing of phonological data. Phon is part of a larger initiative, PhonBank, the brainchild of the first two authors of this paper, which aims at extending the software and database components of the CHILDES project into the realm of phonology. Phon can...
متن کاملRisk assessment of noise pollution by analyzing the level of sound loudness resulting from central traffic in Shiraz
Background: Today, the effects of environmental pollution on human life and human needs, which reduces the level of community health caused by traffic noise in large cities, are clearly visible by creating irritation and pathogenic conditions. The aim of this study was to assess the risk of noise pollution resulted from central traffic in Shiraz by analyzing its indicators and related componen...
متن کامل