• Speech Sciences
• /
• v.14 no.2
• /
• pp.91-103
• /
• 2007

The purpose of this paper is to develop a model enabling to predict the prosody of Korean text-to-speech synthesis using the CART and SKES algorithms. CART prefers a prediction variable in many instances. Therefore, a partition method by F-Test was applied to CART which had reduced the number of instances by grouping phonemes. Furthermore, the quality of the text-to-speech synthesis was evaluated after applying the SKES algorithm to the same data size. For the evaluation, MOS tests were performed on 30 men and women in their twenties. Results showed that the synthesized speech was improved in a more clear and natural manner by applying the SKES algorithm.

• Speech Sciences
• /
• v.15 no.4
• /
• pp.97-105
• /
• 2008

Nowadays an HMM-based text-to-speech system (HTS) has been very widely studied because it needs less memory and low computation complexity and is suitable for embedded systems in comparison with a corpus-based unit concatenation text-to-speech one. It also has the advantage that voice characteristics and the speaking rate of the synthetic speech can be converted easily by modifying HMM parameters appropriately. We implemented an HMM-based Korean text-to-speech system using a small size Korean speech DB and proposes a method to increase the naturalness of the synthetic speech by controlling duration model parameters in the HMM-based Korean text-to speech system. We performed a paired comparison test to verify that theses techniques are effective. The test result with the preference scores of 73.8% has shown the improvement of the naturalness of the synthetic speech through controlling the duration model parameters.

• Speech Sciences
• /
• v.9 no.1
• /
• pp.207-215
• /
• 2002

Perceptual evaluation of duration models of spoken Korean was carried out based on the Classification and Regression Tree (CART) model for text-to-speech conversion. A reference set of durations was produced by a commercial text-to-speech synthesis system for comparison. The duration model which was built in the previous research (Chung & Huckvale, 2001) was applied to a Korean language speech synthesis diphone database, 'Hanmal (HN 1.0)'. The synthetic speech produced by the CART duration model was preferred in the subjective preference test by a small margin and the synthetic speech from the commercial system was superior in the clarity test. In the course of preparing the experiment, a labeled database of spoken Korean with 670 sentences was constructed. As a result of the experiment, a trained duration model for speech synthesis was obtained. The 'Hanmal' diphone database for Korean speech synthesis was also developed as a by-product of the perceptual evaluation.

• Phonetics and Speech Sciences
• /
• v.10 no.1
• /
• pp.39-48
• /
• 2018

A typical statistical parametric speech synthesis (text-to-speech, TTS) system consists of separate modules, such as a text analysis module, an acoustic modeling module, and a speech synthesis module. This causes two problems: 1) expert knowledge of each module is required, and 2) errors generated in each module accumulate passing through each module. An end-to-end TTS system could avoid such problems by synthesizing voice signals directly from an input string. In this study, we implemented an end-to-end Korean TTS system using Google's Tacotron, which is an end-to-end TTS system based on a sequence-to-sequence model with attention mechanism. We used 4392 utterances spoken by a Korean female speaker, an amount that corresponds to 37% of the dataset Google used for training Tacotron. Our system obtained mean opinion score (MOS) 2.98 and degradation mean opinion score (DMOS) 3.25. We will discuss the factors which affected training of the system. Experiments demonstrate that the post-processing network needs to be designed considering output language and input characters and that according to the amount of training data, the maximum value of n for n-grams modeled by the encoder should be small enough.

• Speech Sciences
• /
• v.2
• /
• pp.9-23
• /
• 1997

Through iterative analysis and synthesis experiments on Korean monosyllables, the Korean text-to-speech system was implemented using the phoneme-based formant synthesis method. Since the formants of initial and final consonants in this system showed many variations depending on the medial vowels, the database for each phoneme was made up of formants depending on the medial vowels as well as duration information of transition region. These techniques were needed to improve the intelligibility of synthetic speech. This paper investigates also methods of concatenating the synthesis units to improve the quality of synthetic speech.

• Proceedings of the IEEK Conference
• /
• 2002.06d
• /
• pp.369-372
• /
• 2002

In this paper, we present an improved TTS synthesis system using articulatory synthesis and concatenative synthesis. In concatenative synthesis, segments of speech are excised from spoken utterances and connected to form the desired speech signal. We adopt LPC as a parameter, VQ to reduce the memory capacity, and TD-PSOLA to solve the naturalness problem.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.4E
• /
• pp.31-38
• /
• 2001

A large-scale synthesis database for a unit selection based synthesis method usually retains redundant synthesis unit instances, which are useless to the synthetic speech quality. In this paper, to eliminate those instances from the synthesis database, we proposed a new pruning method called weighted vector quantization (WVQ). The WVQ reflects relative importance of each synthesis unit instance when clustering the similar instances using vector quantization (VQ) technique. The proposed method was compared with two conventional pruning methods through the objective and subjective evaluations of the synthetic speech quality: one to simply limit maximum number of instance, and the other based on normal VQ-based clustering. The proposed method showed the best performance under 50% reduction rates. Over 50% of reduction rates, the synthetic speech quality is not seriously but perceptibly degraded. Using the proposed method, the synthesis database can be efficiently reduced without serious degradation of the synthetic speech quality.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.2
• /
• pp.461-469
• /
• 2000

In the paper, the design and the implementation of the netscape plug-in and the speech synthesis enginegenerating the speech sounds from the text information of the web pages are described. The steps of the generating speech sound from an web pages are the speech synthesis plug-in is activated when the netscape finds the audio/xesp MIME data type embedded in the browsed web page; the HTML file referenced in the EMBED MTML tag is down loaded from the referenced URL to send to the commander object located in the said plug-in; The speech synthesis engine control tags and the text characters are extracted from the down loaded HTML document by the commander object the synthesized speech sounds are generated by the speech synthesis engine. The speech synthesis engine interprets the command streams from the commander objects to call the member functions for the processing of the speech segment data in the data banks. The commander object and the speech synthesis engine are designed as an independent object to enhancethe flexitility and the portability.

• Speech Sciences
• /
• v.1
• /
• pp.295-314
• /
• 1997

In this study, we will implement a flexible formant analysis and synthesis system. In the analysis part, the two-channel (i.e., speech & EGG signals) approach is investigated for accurate estimation of formant information. The EGG signal is used for extracting exact pitch information that is needed for the pitch synchronous LPC analysis and closed phase LPC analysis. In the synthesis part, Klatt formant synthesizer is modified so that the user can change synthesis parameters arbitarily. Experimental results demonstrate the superiority of the two-channel analysis method over the one-channel(speech signal only) method in analysis as well as in synthesis. The implemented system is expected to be very helpful for studing the effects of synthesis parameters on the quality of synthetic speech and for the development of Korean text-to-speech(TTS) system with the formant synthesis method.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.523-529
• /
• 2021

In this paper, we designed and developed an Emotional Speech Synthesis Markup Language (SSML) processor. Multi-speaker emotional speech synthesis technology that can express multiple voice colors and emotional expressions have been developed, and we designed Emotional SSML by extending SSML for multiple voice colors and emotional expressions. The Emotional SSML processor has a graphic user interface and consists of following four components. First, a multi-speaker emotional text editor that can easily mark specific voice colors and emotions on desired positions. Second, an Emotional SSML document generator that creates an Emotional SSML document automatically from the result of the multi-speaker emotional text editor. Third, an Emotional SSML parser that parses the Emotional SSML document. Last, a sequencer to control a multi-speaker and emotional Text-to-Speech (TTS) engine based on the result of the Emotional SSML parser. Based on SSML which is a programming language and platform independent open standard, the Emotional SSML processor can easily integrate with various speech synthesis engines and facilitates the development of multi-speaker emotional text-to-speech applications.