• 전자공학회논문지 IE
• /
• v.43 no.2
• /
• pp.22-29
• /
• 2006

Recently the use of whispered speech has increased due to mobile phone and the necessity of whispered speech recognition is increasing. So various feature vectors, which are mainly used for speech recognition, are applied to their HMMs, normal speech models, whispered speech models, and integrated models with normal speech and whispered speech so as to find out suitable recognition system for whispered speech. The experimental results of recognition test show that the recognition rate of whispered speech applied to normal speech models is too low to be used in practical applications, but separate whispered speech models recognize whispered speech with the highest rates at least 85%. And also integrated models with normal speech and whispered speech score acceptable recognition rate but more study is needed to increase recognition rate. MFCE and PLCC feature vectors score higher recognition rate when applied to separate whispered speech models, but PLCC is the best when a lied to integrated models with normal speech and whispered speech.

• MALSORI
• /
• no.48
• /
• pp.81-91
• /
• 2003

In this paper, we propose a speech recognition method based on independent component analysis (ICA) and spectral enhancement techniques. While ICA tris to separate speech signal from noisy speech using multiple channels, some noise remains by its algorithmic limitations. Spectral enhancement techniques can compensate for lack of ICA's signal separation ability. From the speech recognition experiments with instantaneous and convolved mixing environments, we show that the proposed approach gives much improved recognition accuracies than conventional methods.

• MALSORI
• /
• no.45
• /
• pp.107-115
• /
• 2003

An efficient method that compensates the HMM parameters for the noisy speech recognition is proposed. Instead of assuming some analytical approximations as in the PMC, the proposed method directly re-estimates the HMM parameters by the segmental k-means algorithm. The proposed method has shown improved results compared with the conventional PMC method at reduced computational cost.

• MALSORI
• /
• no.63
• /
• pp.113-124
• /
• 2007

In this paper, we propose a use of confidence vector as an intermediate input feature for multi-stage based speech recognition architecture to improve recognition accuracy. A multi-stage speech recognition structure is introduced as a method to reduce the computational complexity of the decoding procedure and then accomplish faster speech recognition. Conventional multi-stage speech recognition is usually composed of three stages, acoustic search, lexical search, and acoustic re-scoring. In this paper, we focus on improving the accuracy of the lexical decoding by introducing a confidence vector as an input feature instead of phoneme which was used typically. We take experimental results on 220K Korean Point-of-Interest (POI) domain and the experimental results show that the proposed method contributes on improving accuracy.

• MALSORI
• /
• no.51
• /
• pp.151-165
• /
• 2004

For educational and research purposes, a Korean speech recognition platform is designed. It is based on an object-oriented architecture and can be easily modified so that researchers can readily evaluate the performance of a recognition algorithm of interest. This platform will save development time for many who are interested in speech recognition. The platform includes the following modules: Noise reduction, end-point detection, met-frequency cepstral coefficient (MFCC) and perceptually linear prediction (PLP)-based feature extraction, hidden Markov model (HMM)-based acoustic modeling, n-gram language modeling, n-best search, and Korean language processing. The decoder of the platform can handle both lexical search trees for large vocabulary speech recognition and finite-state networks for small-to-medium vocabulary speech recognition. It performs word-dependent n-best search algorithm with a bigram language model in the first forward search stage and then extracts a word lattice and restores each lattice path with a trigram language model in the second stage.

• Phonetics and Speech Sciences
• /
• v.6 no.2
• /
• pp.29-34
• /
• 2014

In the Vector Taylor Series (VTS)-based noisy speech recognition methods, Hidden Markov Models (HMM) are usually trained with clean speech. However, better performance is expected by training the HMM with noisy speech. In a previous study, we could find that Minimum Mean Square Error (MMSE) estimation of the training noisy speech in the log-spectrum domain produce improved recognition results, but since the proposed algorithm was done in the log-spectrum domain, it could not be used for the HMM adaptation. In this paper, we modify the previous algorithm to derive a novel mathematical relation between test and training noisy speech in the cepstrum domain and the mean and covariance of the Multi-condition TRaining (MTR) trained noisy speech HMM are adapted. In the noisy speech recognition experiments on the Aurora 2 database, the proposed method produced 10.6% of relative improvement in Word Error Rates (WERs) over the MTR method while the previous MMSE estimation of the training noisy speech produced 4.3% of relative improvement, which shows the superiority of the proposed method.

• MALSORI
• /
• no.50
• /
• pp.99-110
• /
• 2004

The normal transmission characteristics of sound are hardly obtained due to the various noises and structural factors in a running car environment. It is due to the channel distortion of the original source sound recorded by microphones, and it seriously degrades the performance of the speech recognition in real driving environments. In this paper we analyze the degree of intelligibility under the various sound distortion environments by channels according to driving speed with respect to speech transmission index(STI) and compare the STI with rates of speech recognition. We examine the correlation between measures of intelligibility depending on sound pick-up patterns and performance in speech recognition. Thereby we consider the optimal location of a microphone in single channel environment. In experimentation we find that high correlation is obtained between STI and rates of speech recognition.

• Proceedings of the KIEE Conference
• /
• 1998.07g
• /
• pp.2265-2267
• /
• 1998

This paper deals with study of Fast Speaker Adaptation Type Speech Recognition, and to analyze speech signal efficiently in time domain and time-frequency domain, utilizes SCONN[1] with Speech Signal Process suffices for Fast Speaker Adaptation Type Speech Recognition, and examined Speech Recognition to investigate adaptation of system, which has speech data input after speaker dependent recognition test.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.5
• /
• pp.683-687
• /
• 2010

This paper studied some methods which use frequency warping method that is the one of the speech transformation method to develope the robust speech recognition system for the emotional variation. For this purpose, the effect of emotional variations on the speech signal were studied using speech database containing various emotions and it is observed that speech spectrum is affected by the emotional variation and this effect is one of the reasons that makes the performance of the speech recognition system worse. In this paper, new training method that uses frequency warping in training process is presented to reduce the effect of emotional variation and the speech recognition system based on vocal tract length normalization method is developed to be compared with proposed system. Experimental results from the isolated word recognition using HMM showed that new training method reduced the error rate of the conventional recognition system using speech signal containing various emotions.

• MALSORI
• /
• no.50
• /
• pp.71-83
• /
• 2004

Recently, broadcast news speech recognition has become one of the most attractive research areas. If we can transcribe automatically the broadcast news and store their contents in the text form instead of the video or audio signal itself, it will be much easier for us to search for the multimedia databases to obtain what we need. However, the desirable speech signal in the broadcast news are usually affected by the interfering signals such as the background noise and/or the music. Also, the speech of the reporter who is speaking over the telephone or with the ill-conditioned microphone is severely distorted by the channel effect. The interfered or distorted speech may be the main reason for the poor performance in the broadcast news speech recognition. In this paper, we investigated some methods to cope with the problems and we could see some performance improvements in the noisy broadcast news speech recognition.