• The Journal of the Acoustical Society of Korea
• /
• v.15 no.3E
• /
• 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.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06c
• /
• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.7
• /
• pp.528-538
• /
• 2003

A SCCRS (Speech and Character Combined Recognition System) is developed for working on mobile devices such as PDA (Personal Digital Assistants). In SCCRS, the feature extraction is separately carried out for speech and for hand-written character, but the recognition is performed in a common engine. The recognition engine employs essentially CHMM (Continuous Hidden Markov Model), which consists of variable parameter topology in order to minimize the number of model parameters and to reduce recognition time. For generating contort independent variable parameter model, we propose the SSMS(Successive State and Mixture Splitting), which gives appropriate numbers of mixture and of states through splitting in mixture domain and in time domain. The recognition results show that the proposed SSMS method can reduce the total number of GOPDD (Gaussian Output Probability Density Distribution) up to 40.0% compared to the conventional method with fixed parameter model, at the same recognition performance in speech recognition system.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.3
• /
• pp.56-62
• /
• 2001

In this paper, we adopt a missing data theory to speech recognition. It can be used in order to maintain high performance of speech recognizer when the missing data occurs. In general, hidden Markov model (HMM) is used as a stochastic classifier for speech recognition task. Acoustic events are represented by continuous probability density function in continuous density HMM(CDHMM). The missing data theory has an advantage that can be easily applicable to this CDHMM. A marginalization method is used for processing missing data because it has small complexity and is easy to apply to automatic speech recognition (ASR). Also, a spectral subtraction is used for detecting missing data. If the difference between the energy of speech and that of background noise is below given threshold value, we determine that missing has occurred. We propose a new method that examines the reliability of detected missing data using voicing probability. The voicing probability is used to find voiced frames. It is used to process the missing data in voiced region that has more redundant information than consonants. The experimental results showed that our method improves performance than baseline system that uses spectral subtraction method only. In 452 words isolated word recognition experiment, the proposed method using the voicing probability reduced the average word error rate by 12％ in a typical noise situation.

• Proceedings of the KSPS conference
• /
• 2005.11a
• /
• 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
• /
• v.17 no.2E
• /
• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.4
• /
• pp.31-36
• /
• 2000

This paper describes the implementation and the evaluation of the speech recognition automatic exchange system. The system provides government or public offices, companies, educational institutions that are composed of large number of members and parts with exchange service using speech recognition technology. The recognizer of the system is a Speaker-Independent, Isolated-word, Flexible-Vocabulary recognizer based on SCHMM(Semi-Continuous Hidden Markov Model). For real-time implementation, DSP TMS320C32 made in Texas Instrument Inc. is used. The system operating terminal including the diagnosis of speech recognition DSP and the alternation of speech recognition candidates makes operation easy. In this experiment, 8 speakers pronounced words of 1,300 vocabulary related to automatic exchange system over wire telephone network and the recognition system achieved 91.5% of word accuracy.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1995.06a
• /
• 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.

• MALSORI
• /
• v.55
• /
• 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.

• Speech Sciences
• /
• v.15 no.2
• /
• 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.