The purpose of this study was to examine the acoustic perception different by formants change for profoundly hearing impaired children with cochlear implants. The subjects were 10 children after 15 months of experience with the implant and mean of their chronological age was 8.4 years and Standard deviation was 2.9 years. The ability of auditory perception was assessed using acoustic-synthetic vowels. The acoustic-synthetic vowel was combined with F1, F2, and F3 into a vowel and produced 42 synthetic sound, using Speech GUI(Graphic User Interface) program. The data was deal with clustering analysis and on-line analytical processing for perception ability of acoustic synthetic vowel. The results showed that auditory perception scores of acoustic-synthetic vowels for cochlear implanted children were increased in F2 synthetic vowels compaire to those of F1. And it was found that they perceived the differences of vowels in terms of distance rates between F1 and F2 in specific vowel.

The purpose of this paper is to examine the change of the times on the transmission rate of broadcast message. In order to find out the research results, I collected past recorded news tapes and selected 22 radio news out from era of Japanese Imperialism, 1950's, 1960's and contemporary age. Next I measured each announcer's reading rate, and compared change on news-reading rate between present and past approximately 50 years ago. The results of study with such procedures and methods are as follows : the average reporting rate of newscasters in each era is different. From these results, we can easily grasp diachronic change in the transmission rate of broadcast message. Namely, the results show us that present announcers read news faster than the group of past era of Japanese Imperialism by 68%.

The purpose of this study is to investigate prosodic characteristics in the speech of adults with cerebral palsy through a comparison with the speech of normal speakers. Ten speakers with cerebral palsy (6 males, 4 females) and 6 normal speakers (3 males, 3 females) served as subjects. The results revealed that, compared to normal speakers, speakers with cerebral palsy showed a slower speech rate, a larger number of intonational phrases(IPs) and pauses, a larger number of accentual phrases(APs) per IP, a longer duration of pauses, and more gradual slopes of [L +H] in APs. However, the two groups showed similar tone patterns in their APs. The results also showed mild to moderate correlations between speech intelligibility and the prosodic properties which showed significant differences between the two groups, suggesting that they could be important prosodic factors to predict speech intelligibility in the speech of adults with cerebral palsy.

This study investigates phonation types of Korean obstruents associated with the vowels immediately following singletons or geminates in intervocalic positions. F0, H1-H2, and spectral tilt were measured from the 20 ms segment at the onset of the vowels for the tokens of /paCa/ and /paCCa/, where Cs are of the same manner and place of articulation. The results showed a remarkable change in the values of F0, H1-H2, and spectral tilt as the preceding obstruents shifts from the lenis singletons to the lenis geminates, which suggests that the spectral characteristics of the vowels following the lenis geminates are not different from those of the vowels following fortis singletons or geminates. Significantly enough, this study adds data about the spectral characteristics of Korean phonation types.

Nowadays, mel-frequency cesptral coefficients (MFCCs) and Gaussian mixture models (GMMs) are used for the pathological voice detection. This paper suggests a method to improve the performance of the pathological/normal voice classification based on the MFCC-based GMM. We analyze the characteristics of the mel frequency-based filterbank energies using the fisher discriminant ratio (FDR). And the feature vectors through the linear discriminant analysis (LDA) transformation of the filterbank energies (FBE) and the MFCCs are implemented. An accuracy is measured by the GMM classifier. This paper shows that the FBE LDA-based GMM is a sufficiently distinct method for the pathological/normal voice classification, with a 96.6% classification performance rate. The proposed method shows better performance than the MFCC-based GMM with noticeable improvement of 54.05% in terms of error reduction.

In this paper, we introduce mel-cepstrum modulation energy (MCME) for a feature to discriminate speech and music data. MCME is a mel-cepstrum domain extension of modulation energy (ME). MCME is extracted on the time trajectory of Mel-frequency cepstral coefficients, while ME is based on the spectrum. As cepstral coefficients are mutually uncorrelated, we expect the MCME to perform better than the ME. To find out the best modulation frequency for MCME, we perform experiments with 4 Hz to 20 Hz modulation frequency. To show effectiveness of the proposed feature, MCME, we compare the discrimination accuracy with the results obtained from the ME and the cepstral flux.

Noise reduction technologies are indispensable to achieve acceptable speech quality in VoIP systems. This paper proposes a Wiener filter optimized to the estimated SNR of noisy speech for the noise reduction in VoIP environments. The proposed noise canceller is applied as a pre-processor before speech encoding. The performance of the proposed method is evaluated by the PESQ in various noisy conditions. In this paper, the proposed algorithm is applied to G.711, G.723.1, and G.729A which are all VoIP speech codecs. The PESQ results show that the performance of our proposed noise reduction scheme outperforms those of the noise suppression in the IS-127 EVRC and the ETSI standard for the advanced distributed speech recognition front-end.

Speech signal is distorted by channel characteristics or additive noise and then the performances of speaker or speech recognition are severely degraded. To cope with the noise problem, we propose a modified HMM decoder algorithm using SNR-based observation confidence, which was successfully applied for GMM in speaker identification task. The modification is done by weighting observation probabilities with reliability values obtained from SNR. Also, we apply PSO (particle swarm optimization) method to the confidence function for maximizing the speaker identification performance. To evaluate our proposed method, we used the ETRI database for speaker recognition. The experimental results showed that the performance was definitely enhanced with the modified HMM decoder algorithm.

The pronunciation lexicon of a continuous speech recognition system should contain enough pronunciation variations to be used for building a search space large enough to contain a correct path, whereas the size of the pronunciation lexicon needs to be constrained for effective decoding and lower perplexities. This paper describes a procedure for selecting pronunciation variations to be included in the lexicon based on the frequencies of the corresponding phonetic rules observed in the training corpus. Likelihood of a phonetic rule's application is estimated using the observation frequency of the rule and is used to control the construction of a pronunciation lexicon. Experiments with various pronunciation lexica show that the proposed method is helpful to improve the speech recognition performance.

Discrimination between speech and music is important in many multimedia applications. In our previous work, focusing on the spectral change characteristics of speech and music, we presented a method using the mean of minimum cepstral distances (MMCD), and it showed a very high discrimination performance. In this paper, to further improve the performance, we propose to employ time-averaged MFCC in computing the MMCD. Our experimental results show that the proposed method enhances the discrimination between speech and music. Moreover, the proposed method overcomes the weakness of the conventional MMCD method whose performance is relatively sensitive to the choice of the frame interval to compute the MMCD.