In this study, we investigated acoustic characteristics of imitated utterances by a professional voice imitator, focusing on prosodic properties such as vowel formants and f0 distribution. To see the patterns of a voice imitation by a professional voice imitator, we compared the imitator's voice data with target speakers' voice data. The professional imitator, Mr. Bae produced utterances imitating the former President Kim's, the comedian Choi's, and the singer Bae's voices. Auditorily, the imitator was judged to imitate all the target speakers' voices successfully. However, acoustic examination showed that the imitator was better at imitating the singer Bae's voice in that the imitator's and the singer Bae's voices are more alike with respect to vowel formants and f0 distribution. We infer this is because the imitator's normal voice is very similar to the singer Bae's voice. On the other hand, the imitator's voice data showed that the patterns of vowel formants and f0 distribution found in the imitator's imitation voices of the other two target speakers were different from those of target speakers' voices.

The present study investigates phonation types of the plosives in Bahasa Indonesia in terms of VOT, F0, durations of intervocalic closure, the preceding vowel, and the following vowel. The results showed that two speaker groups have distinct phonation types. Speaker Group I was characterized by a short voice lag for voiceless plosives and a considerable amount of voice lead for voiced ones. Speaker Group II was characterized by a short lag for both voiceless and voiced plosives. Although both groups showed a significant difference in F0 and the durations of individual segments between voiceless and voiced plosives, they had a remarkable difference in the temporal structure of the segments. Speaker Group I had temporal compensation between the intervocalic closure and the surrounding vowels across voice, such that the shorter the intervocalic closure the longer the surrounding vowels, while Speaker Group 2 didn't. This means that there are two different phonation type systems within a language.

The purpose of this paper was to evaluate the effect of hearing level on fundamental frequencies in children. Participants totaled sixty children divided by three groups: congenitally deafened children with cochlear implantation(CI), congenitally deafened children with hearing aids(HA), and children with normal hearing(NH). Fundamental frequencies were measured during the sustained phonation of a vowel /a/. There was statistically significant difference of fundamental frequencies across the groups(p<.01). In post hoc analysis, HA and NH group showed statistically significant difference, but CI group didn't showed significant differences with two groups. In correlation analysis between F0 and the chronological age, there were significant negative tendencies in CI and NH group, but not in HA group. The characteristics of fundamental frequency in CI group were found similar to NH group than HA group in this study. Therefore the results of this study suggest that the hearing level is one of the influencing factors to the fundamental frequency of children.

This study investigates the Korean native speakers' English liquid perception and production. Perception and production experiments were each conducted twice before and after a short period of explicit learning process of phonetic characteristics of English liquids. The results showed that correlation between perception and production varied depending on factors. In both perception and production, word-final position was the most difficult, and cluster position was the easiest. A considerable improvement was observed in word-initial and medial positions in production, whereas no improvement was achieved in word-final position, especially in production. This study is also concerned with the formant structures of Korean native speakers' production of English liquids in order to see what acoustic features are highly correlated with Korean native speakers' production accuracy of English liquids. The results showed that F2 did not show a high correlation while F3 was a strong correlate of the production accuracy.

The aim of this study is to show developmental characteristics of vocabulary of Korean children. In this study, words were classified according to the origin of words: pure Korean, sino-Korean and foreign words. The results of the present study are as follows: In common nouns, the rate of sino-Korean was 33.6% in 3 year-old children but 50.7% in 8 year-old children. Adverb and prenouns showed the similar rate. The rate of words with foreign origin was 10 ～ 11 % in all age groups.

This paper proposes a new confidence measure for utterance verification with posterior probability approximation. The proposed method approximates probabilistic likelihoods by using Viterbi search characteristics and a clustered phoneme confusion matrix. Our measure consists of the weighted linear combination of acoustic and phonetic confidence scores. The proposed algorithm shows better performance even with the reduced computational complexity than those utilizing conventional confidence measures.

This paper focuses on the DSP implementation of an HMM-based speech recognizer that can handle several hundred words of vocabulary size as well as speaker independency. First, we develop an HMM-based speech recognition system on the PC that operates on the frame basis with parallel processing of feature extraction and Viterbi decoding to make the processing delay as small as possible. Many techniques such as linear discriminant analysis, state-based Gaussian selection, and phonetic tied mixture model are employed for reduction of computational burden and memory size. The system is then properly optimized and compiled on the TMS320C6711 DSP for real-time operation. The implemented system uses 486kbytes of memory for data and acoustic models, and 24.5 kbytes for program code. Maximum required time of 29.2 ms for processing a frame of 32 ms of speech validates real-time operation of the implemented system.

This paper is aiming at real-time implementation of adaptive noise cancellation system using DSP processor. ACHARF algorithm, which guarantees stability and fast convergence by adaptive compensator, is used on this DSP system. For the experiments, TLV320AIC23 stereo CODEC of TI Inc. is used with TMS320C6413 DSP processor. Signals of primary input and reference input are obtained by two microphones. The primary input is the voice plus noise signal and the reference input is white noise or real noise. The experimental results show that ANC system using DSP processor with ACHARF is verified to be an effective speech enhancement method for various speech processing units.

The quality of narrowband speech can be enhanced by the bandwidth extension technology. This paper proposes a mixed excitation and an energy compensation method based on Gaussian Mixture Model (GMM). First, we employ the mixed excitation model having both periodic and aperiodic characteristics in frequency domain. We use a filter bank to extract the periodicity features from the filtered signals and model them based on GMM to estimate the mixed excitation. Second, we separate the acoustic space into the voiced and unvoiced parts of speech to compensate for the energy difference between narrowband speech and reconstructed highband, or lowband speech, more accurately. Objective and subjective evaluations show that the quality of wideband speech reconstructed by the proposed method is superior to that by the conventional bandwidth extension method.

In this paper, a new noise compensation method based on the eigenvoice framework in feature space is proposed to reduce the mismatch between training and testing environments. The difference between clean and noisy environments is represented by the linear combination of K eigenvectors that represent the variation among environments. In the proposed method, the performance improvement of speech recognition systems is largely affected by how to construct the noisy models and the bias vector set. In this paper, two methods, the one based on MAP adaptation method and the other using stereo DB, are proposed to construct the noisy models. In experiments using Aurora 2 DB, we obtained 44.86% relative improvement with eigen-environment method in comparison with baseline system. Especially, in clean condition training mode, our proposed method yielded 66.74% relative improvement, which is better performance than several methods previously proposed in Aurora project.

This paper describes the automated call routing for train ticket reservation aid system based on speech recognition. We focus on the task of automatically routing telephone calls based on user's fluently spoken response instead of touch tone menus in an interactive voice response system. Vector-based call routing algorithm is investigated and mapping table for key term is suggested. Korail database collected by KT is used for call routing experiment. We evaluate call-classification experiments for transcribed text from Korail database. In case of small training data, an average call routing error reduction rate of 14% is observed when mapping table is used.