This paper presents durational characteristics of Korean distant-talking speech using speech data, which consist of 500 distant-talking utterances and 500 normal utterances of 10 speakers (5 males and 5 females). Each file was segmented and labeled manually and the duration of each segment and each word was extracted. Using a statistical method, the durational change of distant-talking speech in comparison with normal speech was analyzed. The results show that the duration of words with distant-talking speech is increased in comparison with normal style, and that the average unvoiced consonantal duration is reduced while the average vocalic duration is increased. Female speakers show a stronger tendency towards lengthening the duration in distant-talking speech. Finally, this study also shows that the speakers of distant-talking speech could be classified according to their different duration rate.

The aim of this paper was to analyze the lexical effects on spoken word recognition of Korean monosyllabic word. The lexical factors chosen in this paper was frequency, density and lexical familiarity of words. Result of the analysis was as follows; frequency was the significant factor to predict spoken word recognition score of monosyllabic word. The other factors were not significant. This result suggest that word frequency should be considered in speech perception test.

Existing standard speech coders can provide speech communication of high quality while they degrade the performance of speech recognition systems that use the reconstructed speech by the coders. The main cause of the degradation is that the spectral envelope parameters in speech coding are optimized to speech quality rather than to the performance of speech recognition. For example, mel-frequency cepstral coefficient (MFCC) is generally known to provide better speech recognition performance than linear prediction coefficient (LPC) that is a typical parameter set in speech coding. In this paper, we propose a speech coder using MFCC instead of LPC to improve the performance of a server-based speech recognition system in network environments. However, the main drawback of using MFCC is to develop the efficient MFCC quantization with a low-bit rate. First, we explore the interframe correlation of MFCCs, which results in the predictive quantization of MFCC. Second, a safety-net scheme is proposed to make the MFCC-based speech coder robust to channel error. As a result, we propose a 8.7 kbps MFCC-based CELP coder. It is shown from a PESQ test that the proposed speech coder has a comparable speech quality to 8 kbps G.729 while it is shown that the performance of speech recognition using the proposed speech coder is better than that using G.729.

In this paper, we present a method of generating intonation contour for Korean text-to-speech (TTS) system and a method of synthesizing emotional speech, both based on Soft template mark-up language (Stem-ML), a novel prosody generation model combining mark-up tags and pitch generation in one. The evaluation shows that the intonation contour generated by Stem-ML is better than that by our previous work. It is also found that Stem-ML is a useful tool for generating emotional speech, by controling limited number of tags. Large-size emotional speech database is crucial for more extensive evaluation.

The performance of speech recognition system is degraded by the mismatch between training and test environments. Many studies have been presented to compensate for noise components in the cepstral domain. Recently, higher order cepstral moment normalization method has been introduced to improve recognition accuracy. In this paper, we present real-time high order moment normalization method with post-processing smoothing filter to reduce the parameter estimation error in higher order moment computation. In experiments using Aurora2 database, we obtained error rate reduction of 44.7% with proposed algorithm in comparison with baseline system.

The goal of our research is to build a text-independent speaker identification system that can be used in any condition without any additional adaptation process. The performance of speaker recognition systems can be severely degraded in some unknown mismatched microphone and noise conditions. In this paper, we show that PCA(principal component analysis) can improve the performance in the situation. We also propose an augmented PCA process, which augments class discriminative information to the original feature vectors before PCA transformation and selects the best direction for each pair of highly confusable speakers. The proposed method reduced the relative recognition error by 21%.