• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.5
• /
• pp.649-655
• /
• 2022

In this paper, a determinant-based two-channel noise reduction method which utilizes speech presence probability (SPP) is proposed. The proposed method improves noise reduction performance from the conventional determinant-based two-channel noise reduction method in [7] by applying SPP to the Wiener filter gain. Consequently, the proposed method adaptively controls the amount of noise reduction depending on the SPP. For performance evaluation, the segmental signal-to-noise ratio (SNR), the perceptual evaluation of speech quality, the short time objective intelligibility, and the log spectral distance were measured in the simulated noisy environments considered various types of noise, reverberation, SNR, and the direction and number of noise sources. The experimental results presented that determinant-based methods outperform phase difference-based methods in most cases. In particular, the proposed method achieved the best noise reduction performance maintaining minimum speech distortion.

• Cross-Cultural Studies
• /
• v.48
• /
• pp.223-252
• /
• 2017

This study explores effects of two types of chatbots - voice-based and text-based - on Korean EFL learners' speaking competence and learner perception. Participants were 80 freshmen students taking an English-speaking class at a university in Korea. They were divided into two experimental groups at random. During the sixteen-week experimental period, participants engaged in 10 chat sessions with the two different types of chatbots. To take a close examination of effects on the improvement of speaking competence, they took the TOEIC speaking test as pre- and post-tests. Structured questionnaire-based surveys were conducted before and after treatment to determine if there are changes in perception. Findings reveal two chatbots effectively contribute to improvement of speaking competence among EFL learners. Particularly, the voice-based chatbot was as effective as the text-based chatbot. An analysis of survey results indicates perception of chatbot-assisted language learning changed positively over time. In particular, most participants preferred voice-based chatbot over text-based chatbot. This study provides insight on the use of chatbots in EFL learning, suggesting that EFL teachers should integrate chatbot technology in their classrooms.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.5
• /
• pp.44-51
• /
• 1999

This paper presents a massively parallel computational model for the efficient integration of speech and natural language understanding. The phoneme model is based on continuous Hidden Markov Model with context dependent phonemes, and the language model is based on a knowledge base approach. To construct the knowledge base, we adopt a hierarchically-structured semantic network and a memory-based parsing technique that employs parallel marker-passing as an inference mechanism. Our parallel speech recognition algorithm is implemented in a multi-Transputer system using distributed-memory MIMD multiprocessors. Experimental results show that the parallel speech recognition system performs better in recognition accuracy than a word network-based speech recognition system. The recognition accuracy is further improved by applying code-phoneme statistics. Besides, speedup experiments demonstrate the possibility of constructing a realtime parallel speech recognition system.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.7
• /
• pp.674-679
• /
• 2009

This paper proposes a method of player event retrieval using combination of two functions: detection of player name in speech information and detection of sound event from audio information in golf videos. The system consists of indexing module and retrieval module. At the indexing time audio segmentation and noise reduction are applied to audio stream demultiplexed from the golf videos. The noise-reduced speech is then fed into speech recognizer, which outputs spoken descriptors. The player name and sound event are indexed by the spoken descriptors. At search time, text query is converted into phoneme sequences. The lists of each query term are retrieved through a description matcher to identify full and partial phrase hits. For the retrieval of the player name, this paper compares the results of word-based, phoneme-based, and hybrid approach.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.1
• /
• pp.58-68
• /
• 2005

In this paper, we propose a scheme to improve discriminative property in the feature compensation method for robust speech recognition under noisy environments. The estimation of noisy speech model used in existing feature compensation methods do not guarantee the computation of posterior probabilities which discriminate reliably among the Gaussian components. Estimation of Posterior probabilities is a crucial step in determining the discriminative factor of the Gaussian models, which in turn determines the intelligibility of the restored speech signals. The proposed scheme employs minimum classification error (MCE) training for estimating the parameters of the noisy speech model. For applying the MCE training, we propose to identify and determine the 'competing components' that are expected to affect the discriminative ability. The proposed method is applied to feature compensation based on parallel combined mixture model (PCMM). The performance is examined over Aurora 2.0 database and over the speech recorded inside a car during real driving conditions. The experimental results show improved recognition performance in both simulated environments and real-life conditions. The result verifies the effectiveness of the proposed scheme for increasing the performance of robust speech recognition systems.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.1 s.39
• /
• pp.259-271
• /
• 2006

In this paper, we propose relevant to design and implementation of an integrated management system for various speech corpora. The purpose of this paper is to manage an integrated management system for various kinds of speech corpora necessary for speech research and speech corpora constructed in different data formats. In addition, ways are considered to allow users to search with effect for speech corpora that meet various conditions which they want, and to allow them to add with ease corpora that are constructed newly. In order to achieve this goal, we design a global schema for an integrated management of new additional information without changing old speech corpora, and construct a web-based integrated management system based on the scheme that can be accessed without any temporal and spatial restrictions. Finally, we describe the web based interface which are the executed results involved in the service and show the efficiency of using the index view for implementation of integrated management system.

• Journal of the Korea Convergence Society
• /
• v.11 no.9
• /
• pp.91-97
• /
• 2020

Use of voice-based interfaces that can interact with users is increasing as AI technology develops. To date, however, most of the research on voice-based interfaces has been technical in nature, focused on areas such as improving the accuracy of speech recognition. Thus, the voice of most voice-based interfaces is uniform and does not provide users with differentiated sensibilities. The purpose of this study is to add a emotional factor suitable for the AI interface. To this end, we have derived emotional factors that should be considered in designing voice interface. In addition, we looked at voice trends that differed from country to country. For this study, we conducted interviews with voice industry experts from Finland and Norway, countries that use their own independent languages.

• Proceedings of the KSPS conference
• /
• 2004.05a
• /
• pp.101-123
• /
• 2004

• Information and Communications Magazine
• /
• v.21 no.7
• /
• pp.94-116
• /
• 2004

1968년 ARPA 네트워크의 출현 이후 음성 서비스 위주의 네트워크와 데이터 서비스 위주의 네트워크는 서로의 서비스를 수용하기 위해 노력해왔다. 음성 기반의 네트워크에서 데이터를 수용하기 위한 노력은 ‘꿈의 망’으로 그친 ISDN(Integrated Services Digital Network)으로 나타났고, 데이터 기반의 네트워크에서 음성을 수용하기 위한 노력은 보편적인 비연결형 데이터 서비스와는 대비되는 B-ISDN(Broadband-ISDN)으로 나타났다. 이후 다시 B-ISDN은 IP 서비스의 수용을 위해 ATM 교환기를 MPLS(Multi Protocol Label Switching) 교환기로 대치하여 보완하고 있지만, VoIP(Voice over IP)등 음성서비스의 제공에는 아직 완전한 해법이 제시되지 못하고 있다.(중략)

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.5 no.2
• /
• pp.7-17
• /
• 2001

음성인식 시스템이 있어서 현재 가장 널리 사용되고 있는 Hidden Markov Model(HMM)은 확률 모델을 기반한 것으로 데이터에 대한 통계처리를 학습과정으로 하고 있다. 한국어 연속 숫자음에 대한 음성인식은 고립 숫자음 인식과는 달리 충분한 학습데이터만으로는 만족할 만한 결과를 가져오지 못한다. 이 논문에서는 연속 숫자음 음성인식에 잇어서 비슷하게 발음되는 숫자음과 같은 숫자에 대해 다양하게 발음되는 숫자음에 대해 HMM의 한계를 제시하고 그 해결채으로 Discriminant 학습의 적용방법을 제시한다. 연속 숫자음의 인식 시스템을 구현하는 데 있어서 인식률 낮은 부분에 Discriminant 학습을 적용하여 인식률을 대폭 향상시킨 실험결과를 제시한다.