• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.3
• /
• pp.1-5
• /
• 2002

In this paper, we present an improved grammatical structure of the finite state network(FSN) for constructing useful recognizer of practical Korean price sentences. The grammar constraints of Korean price sentences in the existing method are necessary to modify grammar constraint and grammatical structure for the recognition of practical Korean price sentences. The grammar constraints are improved in the third and the fourth grammar constraint of Korean price sentences for the practical point. In this paper, we improve the grammar constraints and make up for the weak point in the grammatical structure of the FSN[1]. Three kinds of experiments were performed to evaluate the improved grammatical structures; FSN0, FSN-1, FSN-2. As the recognition results for price sentences, the word recognition rates were 81.37%, 83.92%, and 85.49%, for FSN0, FSN-1, and FSN-2. Also, the sentence recognition rates were 35％, 45%, and 52％, respectively.

• MALSORI
• /
• no.50
• /
• pp.123-137
• /
• 2004

In this paper, we consider the implementation of connected digit recognition system using tree structured lexicon model. To implement efficiently the fixed or variable length digit recognition system, finite state network (FSN) is required. We merge the word network algorithm that implements the FSN with lexical tree search algorithm that is used for general speech recognition system for fast search and large vocabulary systems. To find the efficient modeling of digit recognition system, we investigate some performance changes when the lexical tree search is applied.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.11a
• /
• pp.212-215
• /
• 2003

본 논문에서는 숫자음과 단위음으로 구성된 한국어 연결 단위숫자음 인식의 성능 향상을 위하여 한국어 연결 단위숫자음의 특징을 분석하였다. 한국어의 단위숫자음은 숫자음 한음절과 단위음 한음절로 구성된 두음절의 연속적이고 반복적인 발성으로 나타난다. 숫자음에서의 인식 대상 어휘는 숫자음이라는 제한된 규칙을 갖는 가변 숫자음이다. 따라서 개수, 금액, 단위량, 거래량 등에서 나타날 수 있는 가변 숫자음을 인식하기 위하여 FSN(Finite State Network)을 구성하였다. 음향 모델은 한국어 숫자음과 같이 발성구간이 짧은 어휘의 연결음 (connected word)의 인식에서 효과적인 반음절쌍(demi-syllable pair) 모델을 이용하였다 실험결과, 화자 독립적인 가변 숫자음 60문장의 테스트 데이터에 대해서 문장 인식률 91.0%로 인식 성능을 향상시킬 수 있었다.

• MALSORI
• /
• no.45
• /
• pp.47-61
• /
• 2003

In this paper, we consider the implementation of connected digit recognition system and the several approaches to improve its performance. To implement efficiently the fixed or variable length digit recognition system, finite state network (FSN) is required. We merge the word network algorithm that implements the FSN with one pass dynamic programming search algorithm that is used for general speech recognition system for fast search. To find the efficient modeling of digit recognition system, we perform some experiments along the various conditions to affect the performance and summarize the results.

• Journal of Korea Multimedia Society
• /
• v.9 no.1
• /
• pp.23-32
• /
• 2006

This paper describes the optimization of a language model and an acoustic model to improve speech recognition using Korean unit digits. Since the model is composed of a finite state network (FSN) with a disyllable, recognition errors of the language model were reduced by analyzing the grammatical features of Korean unit digits. Acoustic models utilize a demisyllable pair to decrease recognition errors caused by inaccurate division of a phone or monosyllable due to short pronunciation time and articulation. We have used the K-means clustering algorithm with the transformed successive state splitting in the feature level for the efficient modelling of feature of the recognition unit. As a result of experiments, 10.5% recognition rate is raised in the case of the proposed language model. The demi-syllable fair with an acoustic model increased 12.5% recognition rate and 1.5% recognition rate is improved in transformed successive state splitting.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.8
• /
• pp.498-504
• /
• 2005

We introduce a Korean speech recognition platform (ECHOS) developed for education and research Purposes. ECHOS lowers the entry barrier to speech recognition research and can be used as a reference engine by providing elementary speech recognition modules. It has an easy simple object-oriented architecture, implemented in the C++ language with the standard template library. The input of the ECHOS is digital speech data sampled at 8 or 16 kHz. Its output is the 1-best recognition result. N-best recognition results, and a word graph. The recognition engine is composed of MFCC/PLP feature extraction, HMM-based acoustic modeling, n-gram language modeling, finite state network (FSN)- and lexical tree-based search algorithms. It can handle various tasks from isolated word recognition to large vocabulary continuous speech recognition. We compare the performance of ECHOS and hidden Markov model toolkit (HTK) for validation. In an FSN-based task. ECHOS shows similar word accuracy while the recognition time is doubled because of object-oriented implementation. For a 8000-word continuous speech recognition task, using the lexical tree search algorithm different from the algorithm used in HTK, it increases the word error rate by $40\%$ relatively but reduces the recognition time to half.