• 말소리와 음성과학
• /
• 제6권2호
• /
• pp.9-20
• /
• 2014

In this paper, we propose an automatic fluency evaluation algorithm for English speaking tests. In the proposed algorithm, acoustic features are extracted from an input spoken utterance and then fluency score is computed by using support vector regression (SVR). We estimate the parameters of feature modeling and SVR using the speech signals and the corresponding scores by human raters. From the correlation analysis results, it is shown that speech rate, articulation rate, and mean length of runs are best for fluency evaluation. Experimental results show that the correlation between the human score and the SVR score is 0.87 for 3 speaking tests, which suggests the possibility of the proposed algorithm as a secondary fluency evaluation tool.

• 말소리와 음성과학
• /
• 제3권1호
• /
• pp.87-94
• /
• 2011

The decision directed (DD) approach is widely used to determine a priori SNR from noisy speech signals. In conventional speech enhancement systems with a DD approach, a priori SNR is estimated by using only the magnitude components and consequently follows a posteriori SNR with one frame delay. We propose a phase-dependent two-step a priori SNR estimator based on the minimum mean square error (MMSE) in the log-mel spectral domain so that we can consider both magnitude and phase information, and it can overcome the performance degradation caused by one frame delay. From the experimental results, the proposed estimator is shown to improve the output SNR of enhanced speech signals by 2.3 dB compared to the conventional DD approach-based system.

• 말소리와 음성과학
• /
• 제2권4호
• /
• pp.137-143
• /
• 2010

In this paper, a speech endpoint detection algorithm is proposed. The proposed algorithm is a kind of state transition-based ones for speech detection. To reject short-duration acoustic pulses which can be considered noises, it utilizes duration information of all detected pulses. For the optimization of parameters related with pulse lengths and energy threshold to detect speech intervals, an exhaustive search scheme is adopted while speech recognition rates are used as its performance index. Experimental results show that the proposed algorithm outperforms the baseline state-based endpoint detection algorithm. At 5 dB input SNR for the beamforming input, the word recognition accuracies of its outputs were 78.5% for human voice noises and 81.1% for music noises.

• 말소리와 음성과학
• /
• 제2권4호
• /
• pp.145-151
• /
• 2010

In this paper, a robust feature compensation method is proposed for improving the performance of speech recognition. The proposed method is incorporated into the auto-regressive moving average (ARMA) based feature compensation. We employ variable weights for the ARMA filter according to the degree of speech activity, and pass the normalized cepstral sequence through the weighted ARMA filter. Additionally when normalizing the cepstral sequences in training, the cepstral means and variances are estimated from total training utterances. Experimental results show the proposed method significantly improves the speech recognition performance in the noisy and reverberant environments.

• 말소리와 음성과학
• /
• 제2권4호
• /
• pp.153-161
• /
• 2010

Many isolated word recognition systems may generate non-similar words for recognition candidates because they use only acoustic information. The previous study [1,2] investigated several techniques which can exclude non-similar words from N-best candidate words by applying Levenstein distance measure. This paper discusses the various improving techniques of removing non-similar recognition results. The mentioned methods include comparison penalties or weights, phone accuracy based on confusion information, weights candidates by ranking order and partial comparisons. Through experimental results, it is found that some proposed method keeps more accurate recognition results than the previous method's results.

• 말소리와 음성과학
• /
• 제9권2호
• /
• pp.103-110
• /
• 2017

The pole filtering concept has been successfully applied to cepstral feature normalization techniques for noise-robust speech recognition. In this paper, it is proposed to apply the pole filtering selectively only to the speech intervals, in order to further improve the recognition performance for short utterances in noisy environments. Experimental results on AURORA 2 task with clean-condition training show that the proposed selectively pole-filtered cepstral mean normalization (SPFCMN) and selectively pole-filtered cepstral mean and variance normalization (SPFCMVN) yield error rate reduction of 38.6% and 45.8%, respectively, compared to the baseline system.

• 말소리와 음성과학
• /
• 제10권4호
• /
• pp.11-17
• /
• 2018

This study reports on a production experiment designed to investigate how Korean speaking learners of English produce English forms ending in stops. In a repetition experiment, Korean participants listened to English nonce words ending in a stop and repeated what they heard. English speakers were recruited for the same task as a control group. The experimental result indicated that the transcriptions of the Korean productions by English native speakers showed vowel insertion in only 3% of productions although the pronunciation of English final stops showed that noise intervals after the closure of final stops were significantly longer for Korean speakers than for English speakers. This finding is inconsistent with the loanword data where 49% of words showed vowel insertion. It is also not compatible with the perceptual similarity approach, which predicts that because Korean speakers accurately perceive an English final stop as a final consonant, they will insert a vowel to make the English sound more similar to the Korean sound.

• 한국어교육
• /
• 제29권2호
• /
• pp.155-180
• /
• 2018

The purpose of this study is to acoustically analyze eight Korean monophthongs produced by 29 Taiwanese learners of Korean and 20 native speakers of Korean, and to compare their pronunciations in experimental phonetics. Using the first formants(F1) and the second formants(F2) of Korean monophthongs, we can estimate the tongue positions of vowels produced by participants. In order to compare them directly, we had to normalize participants' F1 and F2. The result shows that almost all vowels of the Taiwanese learners are significantly different from those of Korean native speakers in their F1 and F2 values without the /ㅏ/ vowel. In particular, when pronouncing Korean monophthongs, the Korean learners of Taiwan had a narrow area of the place of articulation compared to the Korean native speakers except for back vowels. Finally, it shows that the Korean learners in Taiwan had a narrower range of articulation and articulated the vowels towards the back a little comparing to the Korean native speakers.

• 말소리와 음성과학
• /
• 제1권2호
• /
• pp.51-59
• /
• 2009

This study was designed to investigate the effects of neonatal hearing screening program (NHSP) information on parental satisfaction with the Parent Satisfaction Questionnaire with Neonatal Hearing Screening Program (PSQ-NHSP) by Mazlan et al. (2006). The PSQ-NHSP consisted of four aspects including: information, personnel in charge of the hearing test, appointment activity, and overall satisfaction in the neonatal hearing screening program. A total of 106 parents (50 in the experimental group and 56 in the control group) participated in this study in one general hospital and two delivery clinics. The fifty parents in the experimental group received information and counseling with educational materials before filling out the PSQ-NHSP, but the fifty-six parents in the control group did not receive any counseling or education materials before completing the PSQ-NHSP. The PSQ-NHSP demonstrated excellent internal consistency reliability (${\sigma}=0.914$). The results of the study were as follows. First, the overall satisfaction ($3.77{\pm}0.81$) and personnel in charge of hearing test ($3.52{\pm}0.79$) aspects showed higher rates of satisfaction than the appointment activity aspect ($3.51{\pm}0.80$) for total subjects. Second, the overall parental satisfaction rate of the experimental group ($4.15{\pm}0.50$) was significantly higher than that of the control group ($3.09{\pm}0.53$) in all items. Lastly, thirty-two participants (30%) made at least one comment in response to the open-set items. A total of 29 comments were related to satisfaction with participating in the NHSP and II comments were related to dissatisfaction. In conclusion, to improve parental satisfaction it is important to provide parents with education and information about the NHSP before the test. In addition, PSQ-NHSP was found to be a useful instrument for identifying the benefits and shortfalls of the NHSP.

• 말소리와 음성과학
• /
• 제1권4호
• /
• pp.61-71
• /
• 2009

This study aims to investigate whether the misalignment between syllable and word onsets due to the process of resyllabification affects Korean-English late bilinguals perceiving English continuous speech. Two word-spotting experiments were conducted. In Experiment 1, misalignment conditions (resyllabified conditions) were created by adding CVC contexts at the beginning of vowel-initial words and alignment conditions (non-resyllabified conditions) were made by putting the same CVC contexts at the beginning of consonant-initial words. The results of Experiment 1 showed that detections of targets in alignment conditions were faster and more correct than in misalignment conditions. Experiment 2 was conducted in order to avoid any possibilities that the results of Experiment 1 were due to consonant-initial words being easier to recognize than vowel-initial words. For this reason, all the experimental stimuli of Experiment 2 were vowel-initial words preceded by CVC contexts or CV contexts. Experiment 2 also showed misalignment cost when recognizing words in resyllabified conditions. These results indicate that Korean listeners are influenced by misalignment between syllable and word onsets triggered by a resyllabification process when recognizing words in English connected speech.