• 음성과학
• /
• 제14권2호
• /
• 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.

• 음성과학
• /
• 제15권4호
• /
• 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.

• 음성과학
• /
• 제9권1호
• /
• 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.

• 말소리와 음성과학
• /
• 제10권1호
• /
• 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.

• 음성과학
• /
• 제2권
• /
• 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.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• 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
• /
• 제20권4E호
• /
• 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.

• 한국정보처리학회논문지
• /
• 제7권2호
• /
• pp.461-469
• /
• 2000

본 논문은 인터넷 웹페이지의 텍스트 정보를 추출하여 이를 음성으로 합성하기 위한 음성합성 엔진 및 넷스케이프 플러그인의 설계 및 구현에 관한 것이다. 인터넷 웹페이지를 음성으로 합성하는 방법은 audio/x-esp MIME 타입을 임베딩한 웹페이지가 발견되면서 이에 상응하는 플러그-인이 작되며 해당 플러그인은 URL로 지정된 HTML 문서를 네트워크에서 가져와 컴맨더 모브젝트에 보내교, 컴맨더 오브젝트는 HTML 문서를 파싱하여 합성엔진 제어용 TAG를 추출한다. 제어용 TAG에는 음성합성 데이터베이스 변경 및 합성음의 길이 또는 피치조절 파라미터 등의 정보를 갖고 있어 동적으로 합성음을 제어할 수 있다. 또한 컴맨더 오브젝트는 HTML 문서 내부의 특정 태그로 지정된 문장을 추출하여 전처리 과정을 수행한 후 합성엔진을 위한 컴맨드 스트림을 발생한다. 음성합성엔진은 컴맨드 스트림을 훼치(Fetch)하여 명령어를 해석하고 해당 명령어를 상응하는 멤버함수를 실행하여 음성을 합성한다. 컴맨더 오브젝트와 음성합성엔진은 각각 독립적인 객체로 설계하여 이식성과 유연성을 높인다.

• 음성과학
• /
• 제1권
• /
• 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.

• 한국음향학회지
• /
• 제40권5호
• /
• pp.523-529
• /
• 2021

본 논문에서는 감정 마크업을 포함하는 Speech Synthesis Markup Language(SSML) 처리기를 설계하고 개발하였다. 다양한 음색과 감정 표현이 가능한 음성합성 기술이 개발되고 있으며 다양한 음색 및 감정 음성합성의 응용 확대를 위하여 표준화된 음성 인터페이스 마크업 언어인 SSML을 감정 표현이 가능하도록 확장한 감정 SSML(Emotional SSML)을 설계하였다. 감정 SSML 처리기는 그래픽 사용자 인터페이스로 손쉽게 음색 및 감정을 원하는 텍스트 부분에 표시할 수 있는 다음색 감정 텍스트 편집기, 편집 결과를 감정 SSML 문서로 생성하는 감정 SSML 문서 생성기, 생성된 감정 SSML 문서를 파싱하는 감정 SSML 파서, 감정 SSML 파서의 결과인 다음색 감정 합성 시퀀스를 기반으로 합성기와 연동하여 음성 스트림의 합성 을 제어하는 시퀀서로 구성된다. 본 논문에서 개발한 다음색 감정합성을 위한 감정 SSML 처리기는 프로그래밍 언어 및 플랫폼 독립적인 개방형 표준인 SSML을 기반으로 하여 다양한 음성합성 엔진에 쉽게 연동할 수 있는 구조를 가지며 다양한 음색과 감정 음성합성이 필요한 다양한 응용 개발에 활용될 것으로 기대한다.