• 말소리와 음성과학
• /
• 제4권4호
• /
• pp.87-92
• /
• 2012

Speech enhancement aims to improve speech quality by removing background noise from noisy speech. Independent vector analysis is a type of frequency-domain independent component analysis method that is known to be free from the frequency bin permutation problem in the process of blind source separation from multi-channel inputs. This paper proposed a new method of microphone array based speech enhancement that combines independent vector analysis and beamforming techniques. Independent vector analysis is used to separate speech and noise components from multi-channel noisy speech, and delay-sum beamforming is used to determine the enhanced speech among the separated signals. To verify the effectiveness of the proposed method, experiments for computer simulated multi-channel noisy speech with various signal-to-noise ratios were carried out, and both PESQ and output signal-to-noise ratio were obtained as objective speech quality measures. Experimental results have shown that the proposed method is superior to the conventional microphone array based noise removal approach like GSC beamforming in the speech enhancement.

• 말소리와 음성과학
• /
• 제4권1호
• /
• pp.13-20
• /
• 2012

A lax stop in Korean, one of the three laryngeal contrastive stops, has undergone a sound change in terms of its acoustic properties. Prior production studies described this recent lax stop as being differentiated from tense and aspirated stops primarily by fundamental frequencies (f0). And, the acoustic property of voice onset time (VOT) further separates tense stops from lax and aspirated stops. The current research explores how these two major acoustic parameters of f0 and VOT cue the three stop categories in Korean adult listeners' perception. Thirty-one native speakers of Korean participated in two experimental tasks: categorization judgment and within-category goodness ratings. Two sets of audio stimuli were prepared by synthesizing English and Korean male speakers' CV productions. The findings showed that while f0 cues listeners to lax stops as production patterns would predict, VOT were closely related to listeners' categorization and goodness ratings of lax stops. This suggests that accurate characterizations of the recent lax stop category need to be based on Korean speakers' perceptual behavior as well as production patterns.

• 말소리와 음성과학
• /
• 제4권4호
• /
• pp.79-86
• /
• 2012

In the two-band excitation (TBE) model, maximum voiced frequency (MVF) is the most important feature of the excitation parameter because the synthetic speech quality depends on MVF. Thus, this paper proposes an enhanced MVF estimation scheme based on the peak picking method. In the proposed scheme, the local peak and the peak lobe are picked from the spectrum of a linear predictive residual signal. The normalized distance between neighboring peak lobes is calculated and utilized as a feature to estimate MVF. Experimental results of both objective and subjective tests show that the proposed scheme improves synthetic speech quality compared with that of the conventional one.

• 말소리와 음성과학
• /
• 제2권1호
• /
• pp.71-75
• /
• 2010

The PESQ is an objective speech quality evaluation measure that is known to have a high correlation with a subjective speech quality measure such as MOS. To examine whether it could be useful as an objective quality measure of synthetic speech, we carried out both subjective evaluation tests with MOS and DMOS and an objective evaluation test with PESQ for HMM-based Korean synthetic speech signals and analyzed the correlation between them. Experimental results have shown that the PESQ has correlations of 0.87 with MOS and 0.92 with DMOS. It means that the PESQ holds much promise for evaluating the quality of synthetic Korean speech.

• 말소리와 음성과학
• /
• 제3권3호
• /
• pp.91-98
• /
• 2011

In this paper, a multi-channel speech enhancement method using the linearly constrained minimum variance (LCMV) algorithm and a variable learning rate control is proposed. To control the learning rate for adaptive filters of the LCMV algorithm, the direction of arrival (DOA) is measured for each short-time input signal and the likelihood function of the target speech presence is estimated to control the filter learning rate. Using the likelihood measure, the learning rate is increased during the pure noise interval and decreased during the target speech interval. To optimize the parameter of the mapping function between the likelihood value and the corresponding learning rate, an exhaustive search is performed using the Bark's scale distortion (BSD) as the performance index. Experimental results show that the proposed algorithm outperforms the conventional LCMV with fixed learning rate in the BSD by around 1.5 dB.

• 말소리와 음성과학
• /
• 제4권2호
• /
• pp.73-78
• /
• 2012

Emotion recognition is an important technology in the filed of human-machine interface. To apply speech technology to emotion recognition, this study aims to establish a relationship between emotional groups and their corresponding voice characteristics by investigating various speech features. The speech features related to speech source and vocal tract filter are included. Experimental results show that statistically significant speech parameters for classifying the emotional groups are mainly related to speech sources such as jitter, shimmer, F0 (F0_min, F0_max, F0_mean, F0_std), harmonic parameters (H1, H2, HNR05, HNR15, HNR25, HNR35), and SPI.

• 말소리와 음성과학
• /
• 제1권3호
• /
• pp.109-115
• /
• 2009

Many isolated word recognition systems may generate non-similar words for recognition candidates because they use only acoustic information. In this paper, we investigate several techniques which can exclude non-similar words from N-best candidate words by applying Levenstein distance measure. At first, word distance method based on phone and syllable distances are considered. These methods use just Levenstein distance on phones or double Levenstein distance algorithm on syllables of candidates. Next, word similarity approaches are presented that they use characters' position information of word candidates. Each character's position is labeled to inserted, deleted, and correct position after alignment between source and target string. The word similarities are obtained from characters' positional probabilities which mean the frequency ratio of the same characters' observations on the position. From experimental results, we can find that the proposed methods are effective for removing non-similar words without loss of system performance from the N-best recognition candidates of the systems.

• 말소리와 음성과학
• /
• 제1권3호
• /
• pp.87-93
• /
• 2009

The purpose of this experimental study is to investigate and compare the vowel lengths of English diphthongs and low vowels among native-English-speaking Americans and Korean college exchange students. To do this eight words and sixteen sentences were uttered and recorded by nine subjects, five Korean subjects and four American subjects. Results showed that the vowel lengths of English low vowels between American subjects and Korean subjects were different, which may lead to foreign accent of Korean speakers. Comparing the average length of English low vowels of Korean subjects with those of American subjects, we can see that American subjects tend to pronounce the English low vowels longer than Korean subjects do. In the pronunciation of diphthongs /eI/ and /ou/, Korean subjects pronounced longer than American subjects did. However, in the pronunciation of diphthongs /au/, /aI/, and /ɔI/, American subjects pronounced longer than Korean subjects did.

• 말소리와 음성과학
• /
• 제1권3호
• /
• pp.95-102
• /
• 2009

In this paper, an efficient target speech detection algorithm is proposed for the performance improvement of multi-input speech enhancement. Using the normalized cross correlation value between two selected channels, the proposed algorithm estimates the probabilistic distribution function of the value from the pure noise interval. Then, log-likelihoods are calculated with the function and the normalized cross correlation value to detect the target speech interval precisely. The detection results are applied to the generalized sidelobe canceller-based algorithm. Experimental results show that the proposed algorithm significantly improves the speech recognition performance and the signal-to-noise ratios.

• 말소리와 음성과학
• /
• 제6권2호
• /
• pp.3-8
• /
• 2014

This paper deals with how mental fatigue has an effect on human voice. For this a monotonous task to increase the feeling of the fatigue and a set of subjective questionnaire for rating the fatigue were designed. From the experiments the designed task was proven to be monotonous based on the results of the questionnaire responses. To investigate a statistical relationship between speech features extracted from the collected speech data and fatigue, the T test for two-related-samples was used. Statistical analysis shows that speech parameters deeply related to the fatigue are the first formant bandwidth, Jitter, H1-H2, cepstral peak prominence, and harmonics-to-noise ratio. According to the experimental results, it can be seen that voice is changed to be breathy as mental fatigue proceeds.