A New Korean Speech Synthesis System and Temporal Model
نویسندگان
چکیده
This paper introduces a new publicly-available Korean diphone database for speech synthesis and reports on our latest work towards a model of Korean prosody. The diphone database is compatible with the MBROLA programme of high-quality multilingual speech synthesis systems. The first part of the paper describes the phonetic and phonological structure of the database and describes how it was recorded and processed. The second part of the paper reports on progress towards a model of segmental timing compatible with diphone synthesis of Korean. So far we have built a model of vowel duration based on the analysis of over 1000 syllables annotated for their segmental and suprasegmental contexts. Through the use of an automated search and error minimisation procedure we have estimated the parameters of a nine-factor model which explains over 80% of the variance in vowel duration in the training data.
منابع مشابه
P-15: Effect of Consumption of Korean Red Ginseng and Sodium Valproate on Apoptosis of Spermatogenic Cells and Sperm Quality in Pilockarpin-Induced Epilepsy Rat Model
Background Reproductive dysfunction and endocrine disorders are common among men with complex partial seizures of temporal lobe origin. Diminished sexual desire and responsiveness along with decreased libido and less orgasm are frequently described in men with temporal lobe epilepsy (TLE). It appears that the reduced fertility in epileptic men is accompanied by erectile dysfunction and abnormal...
متن کاملPhoneme Classification Using Temporal Tracking of Speech Clusters in Spectro-temporal Domain
This article presents a new feature extraction technique based on the temporal tracking of clusters in spectro-temporal features space. In the proposed method, auditory cortical outputs were clustered. The attributes of speech clusters were extracted as secondary features. However, the shape and position of speech clusters change during the time. The clusters temporally tracked and temporal tra...
متن کاملKT-STS: a speech translation system for hotel reservation and a continuous speech recognition system for speech translation
In this paper, we present KT-STS(Korea Telecom Speech Translation System) and a continuous speech recognition system for speech translation. KT-STS is an experimental speech-to-speech translation system which translates a spoken utterance in Korean into one in Japanese. The system has been designed around the task of hotel reservation (dialogues between a Korean customer and a hotel reservation...
متن کاملA prosodic phrasing model for a Korean text-to-speech synthesis system
This paper presents a prosodic phrasing model for Korean to be used in a textto-speech synthesis (TTS) system. Read text corpora were morpho-syntactically parsed and prosodically labeled following the Penn Korean Treebank [Han et al., 2002] and K-ToBI prosodic labeling conventions [Sun-Ah, 2000] respectively. Decision trees were trained with morpho-syntactic and textual distance features to pre...
متن کاملSpoken Term Detection for Persian News of Islamic Republic of Iran Broadcasting
Islamic Republic of Iran Broadcasting (IRIB) as one of the biggest broadcasting organizations, produces thousands of hours of media content daily. Accordingly, the IRIBchr('39')s archive is one of the richest archives in Iran containing a huge amount of multimedia data. Monitoring this massive volume of data, and brows and retrieval of this archive is one of the key issues for this broadcasting...
متن کامل