• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.328-329
• /
• 2007

본 논문은 로봇과 같이 외부 음향잡음에 노출되어 있는 상황 하에서, 대면하고 있는 사람이 입술을 움직여 발성하는 경우에만 음성인식 기능이 수행되도록 하기 위한 방안의 일환으로, 입술움직임 영상을 보다 정확히 추적하기 위한 테스트 환경 구현에 관한 것이다. 음성구간 검출과정에서 입술움직임 영상 추적결과의 활용여부는 입술움직임을 얼마나 정확하게 추적할 수 있느냐에 달려있다. 이를 위해 영상 프레임율 동적 제어, 칼라/이진영상 변환, 순간 캡쳐, 녹화 및 재생기능을 구현함으로써, 다각적인 방향에서 입술움직임 영상 추적기능을 확인해 볼 수 있도록 하였다. 음성/영상기능을 연동시킨 결과 약 99.3%의 연동성공율을 보였다.

• Proceedings of the KSPS conference
• /
• 2005.04a
• /
• pp.87-90
• /
• 2005

Today's state-of the-art speech recognition systems typically use continuous distribution hidden Markov models with the mixtures of Gaussian distributions. To obtain higher recognition accuracy, the hidden Markov models typically require huge number of Gaussian distributions. Such speech recognition systems have problems that they require too much memory to run, and are too slow for large applications. Many approaches are proposed for the design of compact acoustic models. One of those models is subspace distribution clustering hidden Markov model. Subspace distribution clustering hidden Markov model can represent original full-space distributions as some combinations of a small number of subspace distribution codebooks. Therefore, how to make the codebook is an important issue in this approach. In this paper, we report some experimental results on various quantization methods to make more accurate models.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.4
• /
• pp.1299-1304
• /
• 2000

In a speed coding system using excitation source of voiced and unvoiced, it would be involved a distortion of speech quality in case coexist with a voiced and an unvoiced consonants in a frame. So, I propose TSIUVC(Transition Segment Including UnVoiced Consonant) searching, extraction ad approximation-synthesis method in order to uncoexistent with a voiced and unvoiced consonants in a frame. This method based on a zerocrossing rate and pitch detector using FIR-STREAK Digital Filter. As a result, the extraction rates of TSIUVC are 84.8% (plosive), 94.9%(fricative), 92.3%(affricative) in female voice, and 88%(plosive), 94.9%(fricative), 92.3%(affricative) in male voice respectively, Also, I obain a high quality approximation-synthesis waveforms within TSIUVC by using frequency information of 0.547kHz below and 2.813kHz above. This method has the capability of being applied to speech coding of low bit rate, speech analysis and speech synthesis.

• Journal of Information Processing Systems
• /
• v.12 no.3
• /
• pp.410-421
• /
• 2016

In this paper, we propose a framework that attempts to incorporate landmarks into a segment-based Mandarin speech recognition system. In this method, landmarks provide boundary information and phonetic class information, and the information is used to direct the decoding process. To prove the validity of this method, two kinds of landmarks that can be reliably detected are used to direct the decoding process of a segment model (SM) based Mandarin LVCSR (large vocabulary continuous speech recognition) system. The results of our experiment show that about 30% decoding time can be saved without an obvious decrease in recognition accuracy. Thus, the potential of our method is demonstrated.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2001.06a
• /
• pp.281-284
• /
• 2001

In this paper, we present a car number retrieving system using speech recogntion and speech synthesis for PDA. This system consist of 4-digit numbers and command speech recognition as well its speech synthesis. Experiment results showed 4-digit numbers recognition rate 97% and commands recognition 99% through speaker-independent method.

• ETRI Journal
• /
• v.19 no.3
• /
• pp.242-258
• /
• 1997

The Qualcomm code excited linear prediction (QCELP) speech coder was adopted to increase the capacity of the CDMA Mobile System (CMS). In this paper, we implemented the QCELP speech coding algorithm by using TMS320C50 fixed point DSP chip. Also the fixed point simulation was done with C language. The computation complexity of QCELP on TMS320C50 was 10k words and data memory was 4k words. In the normal call test on the CMS, where mobile to mobile call test was done in the bypass mode without double vocoding, mean opinion score for the speech quality was he Qualcomm code excited linear prediction (QCELP) speech quality was 3.11.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.18-21
• /
• 2003

In general it has been considered to be the difficult problem that we divide continuous speech into short interval with having identical phoneme quality. In this paper we used Gaussian Mixture Model (GMM) related to probability density to divide speech into phonemes, an initial, medial, and final sound. From them we peformed continuous speech recognition. Decision boundary of phonemes is determined by algorithm with maximum frequency in a short interval. Recognition process is performed by Continuous Hidden Markov Model(CHMM), and we compared it with another phoneme divided by eye-measurement. For the experiments result we confirmed that the method we presented is relatively superior in auto-segmentation in korean speech.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.333-335
• /
• 2022

The development of speech recognition processing technology has been applied and used in various video and streaming services along with STT and TTS technologies. However, there are high barriers to clear written expression due to the use of dialects and overlapping of stop words, exclamations, and similar words for voice recognition of actual conversation content. In this study, for ambiguous dialects in speech recognition, we propose a speech recognition technology that applies dialect key word dictionary processing method by category and dialect prosody as speech recognition network model properties.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.171-176
• /
• 2023

This study is about a speech recognition error correction system designed to detect and correct speech recognition errors before natural language processing to increase the success rate of intent analysis in natural language processing with optimal efficiency in various service domains. An encoder is constructed to embedded the correct speech token and one or more error speech tokens corresponding to the correct speech token so that they are all located in a dense vector space for each correct token with similar vector values. One or more utterance tokens within a preset Manhattan distance based on the correct utterance token in the dense vector space for each embedded correct utterance token are detected through an error detector, and the correct answer closest to the detected error utterance token is based on the Manhattan distance. Errors are corrected by extracting the utterance token as the correct answer.

• Phonetics and Speech Sciences
• /
• v.6 no.1
• /
• pp.71-76
• /
• 2014

In this paper voice quality of normal speech is qualitatively classified by five components of breathy, creaky, rough, nasal, and thin/thick voice. To determine whether a correlation exists between a subjective measure of voice and an objective measure of voice, each voice is perceptually evaluated using the 1/2/3 scale by speech processing specialists and acoustically analyzed using speech analysis tools such as the Praat, MDVP, and VoiceSauce. The speech parameters include features related to speech source and vocal tract filter. Statistical analysis uses a two-independent-samples non-parametric test. Experimental results show that statistical analysis identified a significant correlation between the speech feature parameters and the components of voice quality.