• The Journal of the Acoustical Society of Korea
• /
• 제15권3E호
• /
• pp.60-65
• /
• 1996

This paper describes on the Korean continuous speech recognition system for flight reservation. It adopts a frame-synchronous One-Pass DP search algorithm driven by syntactic constraints of context free grammar(CFG). For recognition, 48 phoneme-like units(PLU) were defined and used as basic units for acoustic modeling of Korean. This modeling was conducted using a HMM technique, where each model has 4-states 3-continuous output probability distributions and 3-discrete-duration distributions. Language modeling by CFG was also applied to the task domain of flight reservation, which consisted of 346 words and 422 rewriting rules. In the tests, the sentence recognition rate of 62.6% was obtained after speaker adaptation.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1994년도 제11회 음성통신 및 신호처리 워크샵 논문집 (SCAS 11권 1호)
• /
• pp.223-228
• /
• 1994

We propose a novel method to incorporate temporal correlations into a speech recognition system based on the conventional hidden Markov model. With the proposed method using the extended logarithmic pool, we approximate a joint conditional PD by separate conditional PD's associated with respective components of conditions. We provide a constrained optimization algorithm with which we can find the optimal value for the pooling weights. The results in the experiments of speaker-independent continuous speech recognition with frame correlations show error reduction by 13.7% with the proposed methods as compared to that without frame correlations.

• 한국음향학회지
• /
• 제22권7호
• /
• pp.528-538
• /
• 2003

음성 문자 공용 인식 시스템은 PDA (Personal Digital Assistants)와 같은 휴대용 모빌 환경에서 음성인식과 문자인식을 적용하기에 적합하도록 개발되었다. 공용 인식 시스템은 특징 파라미터 추출에 있어서는 음성과 문자부분이 독립적으로 수행되나, 인식 과정은 단일 엔진으로 수행된다. CHMM (Continuous Hidden Markov Model)을 이용하는 인식엔진은 고정 파라미터 모델 구조 대신에 동일한 인식률을 유지하면서 모델의 파라미터의 수를 효과적으로 줄일 수 있는 가변 파라미터 모델 구조를 사용하는 것이 유리하다. 본 논문에서는 문맥 독립 가변 파라미터 모델을 생성하기 위해 SSMS (Successive State and Mixture Splitting) 방법을 제안한다. SSMS 알고리즘은 시간 방향 분할과 혼합수 방향분할을 통해 적절한 상태수와 각 상태당 적절한 혼합수를 가지는 모델을 생성한다. 음성 인식 실험 결과 동일한 인식성능을 나타내는 경우 SSMS 기반 가변 파라미터 모델이 고정 파라미터 모델에 비해 GOPDD (Gaussian Output Probability Density Distribution)의 수가 40% 감소함을 확인할 수 있었다.

• 한국음향학회지
• /
• 제20권3호
• /
• pp.56-62
• /
• 2001

본 논문에서는 손실이 발생하는 상황에서 높은 인식률을 유지하기 위해서 손실 데이터 이론을 음성 인식기에 적용하였다 손실 데이터 이론은 일반적으로 이용되는 통계적 정합 방법인 은닉 마코프 모델 (HMM: hidden Markov model) 중 연속 Gaussian확률 밀도 함수를 이용하여 음성 특징들의 출력 확률을 나타내는 경우에 쉽게 적용할 수 있다는 장점을 갖고 있다. 손실 데이터 이론의 방법 중 계산량이 적고 인식기에 적용이 쉬운 주변화(marginalization)방법을 사용하였으며 특징 벡터의 특정 차수나 시간열의 손실 검출 방법은 음성 신호의 에너지와 주위 배경 잡음의 에너지의 차이가 임계치보다 작게 되는 부분을 찾는 주파수 차감 방법을 이용하였다. 본 논문에서 제안한 손실 영역의 신뢰도 평가는 분석 구간이 모음일 확률을 계산해서 비교적 잉여 정보가 많이 포함된 모음화된 구간의 손실만을 처리하도록 하였다. 제안한 방법을 사용하여 여러 잡음 환경에 대해서 기존의 손실 데이터 처리 방법만을 사용한 경우보다 452 단어의 화자독립 단어 인식 실험을 수행한 결과 오류율측면에서 평균적으로 약 12％의 성능 향상을 얻을 수 있었다.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2005년도 추계 학술대회 발표논문집
• /
• pp.147-150
• /
• 2005

The performance of speech recognition in car environment is severely degraded when there is music or news coming from a radio or a CD player. Since reference signals are available from the audio unit in the car, it is possible to remove them with an adaptive filter. In this paper, we present experimental results of speech recognition in car environment using the echo canceller. For this, we generate test speech signals by adding music or news to the car noisy speech from Aurora2 DB. The HTK-based continuous HMT system is constructed for a recognition system. In addition, the MMSE-STSA method is used to the output of the echo canceller to remove the residual noise more.

• The Journal of the Acoustical Society of Korea
• /
• 제17권2E호
• /
• pp.31-37
• /
• 1998

This paper proposes a feature extraction method using wavelet transform for speech recognition. Speech recognition system generally carries out the recognition task based on speech features which are usually obtained via time-frequency representations such as Short-Time Fourier Transform (STFT) and Linear Predictive Coding(LPC). In some respects these methods may not be suitable for representing highly complex speech characteristics. They map the speech features with same may not frequency resolutions at all frequencies. Wavelet transform overcomes some of these limitations. Wavelet transform captures signal with fine time resolutions at high frequencies and fine frequency resolutions at low frequencies, which may present a significant advantage when analyzing highly localized speech events. Based on this motivation, this paper investigates the effectiveness of wavelet transform for feature extraction of wavelet transform for feature extraction focused on enhancing speech recognition. The proposed method is implemented using Sampled Continuous Wavelet Transform (SCWT) and its performance is tested on a speaker-independent isolated word recognizer that discerns 50 Korean words. In particular, the effect of mother wavelet employed and number of voices per octave on the performance of proposed method is investigated. Also the influence on the size of mother wavelet on the performance of proposed method is discussed. Throughout the experiments, the performance of proposed method is discussed. Throughout the experiments, the performance of proposed method is compared with the most prevalent conventional method, MFCC (Mel0frequency Cepstral Coefficient). The experiments show that the recognition performance of the proposed method is better than that of MFCC. But the improvement is marginal while, due to the dimensionality increase, the computational loads of proposed method is substantially greater than that of MFCC.

• 한국음향학회지
• /
• 제19권4호
• /
• pp.31-36
• /
• 2000

본 논문에서는 음성 인식을 이용한 자동 교환 시스템을 구현하고, 성능을 평가하였다. 이 시스템은 다수의 구성원과 조직 체계를 가지는 관공서나 일반 기업, 학교 등의 교환 서비스를 음성 인식을 통하여 자동으로 제공한다. 본 시스템에 사용된 음성 인식기는 SCHMM(Semi-Continuous Hidden Markov Model) 기반으로 한 전화망에서의 화자 독립 고립 단어 가변 어휘인식기(Speaker-Independent, Isolated-Word, Flexible-Vocabulary Recognizer)이며, 실시간 구현을 위해 사용한 DSP(Digital Signal Processor)는 Texas Instrument 사의 TMS320C32이다. 자동 교환 서비스를 위하여 음성 인식 기능 외에도 음성 인식 DSP 진단 기능과 인식 대상 어휘의 추가 및 변경을 위한 운용 단말을 구현하여 운용의 편의성을 추구하였다. 본 시스템의 인식 실험은 음성 인식 구내 자동 교환 시스템용 1300여 어휘(부서명, 인명 등)에 대해서 8명의 화자가 유선 전화망에서 수행하였으며 인식률은 91.5%이다.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1995년도 제12회 음성통신 및 신호처리 워크샵 논문집 (SCAS 12권 1호)
• /
• pp.184-187
• /
• 1995

This paper proposes an algorithm for machine recognition of phonemes in continuous speech. The proposed algorithm is static strategy neural network. The algorithm uses, at the stage of training neuron, features such as PARCOR coefficient and auditory-like perceptual liner prediction . These features are extracted from speech samples selected by a sliding 25.6msec windows with s sliding gap being 3 msec long, then interleaved and summed up to 7 sets of parmeters covering 171 msec worth of speech for use of neural inputs. Perfomances are compared when either PARCOR or auditory-like PLP is included in the feture set.

• 대한음성학회지:말소리
• /
• 제55권
• /
• pp.103-118
• /
• 2005

In this paper, we describe a morpheme-based pronunciation lexicon useful for Korean LVCSR. The phonemic-context-dependent multiple pronunciation lexicon improves the recognition accuracy when cross-morpheme pronunciation variations are distinguished from within-morpheme pronunciation variations. Since adding all possible pronunciation variants to the lexicon increases the lexicon size and confusability between lexical entries, we have developed a lexicon pruning scheme for optimal selection of pronunciation variants to improve the performance of Korean LVCSR. By building a proposed pronunciation lexicon, an absolute reduction of $0.56\%$ in WER from the baseline performance of $27.39\%$ WER is achieved by cross-morpheme pronunciation variations model with a phonemic-context-dependent multiple pronunciation lexicon. On the best performance, an additional reduction of the lexicon size by $5.36\%$ is achieved from the same lexical entries.

• 음성과학
• /
• 제15권2호
• /
• pp.55-65
• /
• 2008

Recently, the multi-model based speech recognizer has been used quite successfully for noisy speech recognition. For the selection of the reference HMM (hidden Markov model) which best matches the noise type and SNR (signal to noise ratio) of the input testing speech, the estimation of the SNR value using the VAD (voice activity detection) algorithm and the classification of the noise type based on the GMM (Gaussian mixture model) have been done separately in the multi-model framework. As the SNR estimation process is vulnerable to errors, we propose an efficient method which can classify simultaneously the SNR values and noise types. The KL (Kullback-Leibler) distance between the single Gaussian distributions for the noise signal during the training and testing is utilized for the classification. The recognition experiments have been done on the Aurora 2 database showing the usefulness of the model compensation method in the multi-model based speech recognizer. We could also see that further performance improvement was achievable by combining the probability density function of the MCT (multi-condition training) with that of the reference HMM compensated by the D-JA (data-driven Jacobian adaptation) in the multi-model based speech recognizer.