• ETRI Journal
• /
• v.29 no.4
• /
• pp.527-529
• /
• 2007

In this paper, a decision-tree-based Markov model for phrase break prediction is proposed. The model takes advantage of the non-homogeneous-features-based classification ability of decision tree and temporal break sequence modeling based on the Markov process. For this experiment, a text corpus tagged with parts-of-speech and three break strength levels is prepared and evaluated. The complex feature set, textual conditions, and prior knowledge are utilized; and chunking rules are applied to the search results. The proposed model shows an error reduction rate of about 11.6% compared to the conventional classification model.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.33 no.3
• /
• pp.142-155
• /
• 2022

Diagnosis using voice is non-invasive and can be implemented through various voice recording devices; therefore, it can be used as a screening or diagnostic assistant tool for laryngeal voice disease to help clinicians. The development of artificial intelligence algorithms, such as machine learning, led by the latest deep learning technology, began with a binary classification that distinguishes normal and pathological voices; consequently, it has contributed in improving the accuracy of multi-classification to classify various types of pathological voices. However, no conclusions that can be applied in the clinical field have yet been achieved. Most studies on pathological speech classification using speech have used the continuous short vowel /ah/, which is relatively easier than using continuous or running speech. However, continuous speech has the potential to derive more accurate results as additional information can be obtained from the change in the voice signal over time. In this review, explanations of terms related to artificial intelligence research, and the latest trends in machine learning and deep learning algorithms are reviewed; furthermore, the latest research results and limitations are introduced to provide future directions for researchers.

• Speech Sciences
• /
• v.7 no.1
• /
• pp.217-232
• /
• 2000

In this study, I investigate the role of post-consonantal fundamental frequency (F0) as a cue for automatic distinction of types of Korean stops and affricates. Rather than examining data obtained by restricting contexts to a minimum to prevent the interference of irrelevant factors, a relatively natural speaker independent speech corpus is analysed. Automatic and statistical approaches are adopted to annotate data, to minimise speaker variability, and to evaluate the results. In spite of possible loss of information during those automatic analyses, statistics obtained suggest that vowel F0 is a useful cue for distinguishing manners of articulation of Korean non-continuant obstruents having the same place of articulation, especially of lax and aspirated stops and affricates. On the basis of the statistics, automatic classification is attempted over the relevant consonants in a specific context where the micro-prosodic effects appear to be maximised. The results confirm the usefulness of this effect in application for Korean phone recognition.

• Smart Media Journal
• /
• v.11 no.11
• /
• pp.17-24
• /
• 2022

With the spread of smart speakers based on voice recognition technology and deep learning technology, not only non-disabled people, but also the blind or physically handicapped can easily control home appliances such as lights and TVs through voice by linking home network services. This has greatly improved the quality of life. However, in the case of speech-impaired people, it is impossible to use the useful services of the smart speaker because they have inaccurate pronunciation due to articulation or speech disorders. In this paper, we propose a personalized voice classification technique for the speech-impaired to use for some of the functions provided by the smart speaker. The goal of this paper is to increase the recognition rate and accuracy of sentences spoken by speech-impaired people even with a small amount of data and a short learning time so that the service provided by the smart speaker can be actually used. In this paper, data augmentation and one cycle learning rate optimization technique were applied while fine-tuning ResNet18 model. Through an experiment, after recording 10 times for each 30 smart speaker commands, and learning within 3 minutes, the speech classification recognition rate was about 95.2%.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.3
• /
• pp.285-292
• /
• 2002

One of the problems that should be solved in Text-To-Speech (TTS) is discontinuities at unit-joining points. To cope with this problem, a smoothing method using a low-pass filter is employed in this paper, In the proposed soothing method, a filter coefficient that controls the amount of smoothing is determined according to contort information to be synthesized. This method efficiently reduces both discontinuities at unit-joining points and artifacts caused by undesired smoothing. The amount of smoothing is determined with discontinuities around unit-joins points in the current synthesized speech and discontinuities predicted from context. The discontinuity predictor is implemented by CART that has context feature variables. To evaluate the performance of the proposed method, a corpus-based concatenative TTS was used as a baseline system. More than 6075 of listeners realized that the quality of the synthesized speech through the proposed smoothing is superior to that of non-smoothing synthesized speech in both naturalness and intelligibility.

• The Journal of the Acoustical Society of Korea
• /
• v.32 no.2
• /
• pp.157-166
• /
• 2013

This paper proposes a non-intrusive speech quality estimation method considering the effects of packet loss to perceptual quality. Packet loss is a major reason of quality degradation in a packet based speech communications network, whose effects are different according to the input speech characteristics or the performance of the embedded packet loss concealment (PLC) algorithm. For the quality estimation system that involves packet loss effects, we first observe the packet loss of G.729 codec which is one of narrowband codec in VoIP system. In order to quantify the lost packet affects, we design a classification algorithm only using speech parameters of G.729 decoder. Then, the degradation values of each class are iteratively selected that maximizes the correlation with the degradation PESQ-LQ scores, and total quality degradation is modeled by the weighted sum. From analyzing the correlation measures, we obtained correlation values of 0.8950 for the intrusive model and 0.8911 for the non-intrusive method.

• Phonetics and Speech Sciences
• /
• v.4 no.2
• /
• pp.95-104
• /
• 2012

Thyroidectomy patients may have vocal paralysis or paresis, resulting in a breathy voice. The aim of this study was to investigate the aerodynamic and acoustic characteristics of a breathy voice in thyroidectomy patients. Thirty-five subjects who have vocal paralysis after thyroidectomy participated in this study. According to perceptual judgements by three speech pathologists and one phonetic scholar, subjects were divided into two groups: breathy voice group (n = 21) and non-breathy voice group (n = 14). Aerodynamic analysis was conducted by three tasks (Voicing Efficiency, Maximum Sustained Phonation, Vital Capacity) and acoustic analysis was measured during Maximum Sustained Phonation task. The breathy voice group had significantly higher subglottal pressure and more pathological voice characteristics than the non breathy voice group. Showing 94.1% classification accuracy in result logistic regression of aerodynamic analysis, the predictor parameters for breathiness were maximum sound pressure level, sound pressure level range, phonation time of Maximum Sustained Phonation task and Pitch range, peak air pressure, and mean peak air pressure of Voicing Efficiency task. Classification accuracy of acoustic logistic regression was 88.6%, and five frequency perturbation parameters were shown as predictors. Vocal paralysis creates air turbulence at the glottis. It fluctuates frequency-related parameters and increases aspiration in high frequency areas. These changes determine perceptual breathiness.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.7
• /
• pp.945-951
• /
• 2007

Noise cancellation is essential for the devices which use speech as an interface. In real environments, speech quality and recognition rates are degraded by the auditive noises coming near the microphone. In this paper, we propose a noise cancellation algorithm using stereo microphones basically. The advantage of the use of multiple microphones is that the direction information of the target source could be applied. The proposed noise canceller is based on the Wiener filter. To estimate the filter, noise and target speech frequency responses should be known and they are estimated by the spectral classification in the frequency domain. The performance of the proposed algorithm is compared with that of the well-known Frost algorithm and the generalized sidelobe canceller (GSC) with an adaptation mode controller (AMC). As performance measures, the perceptual evaluation of speech quality (PESQ), which is the most widely used among various objective speech quality methods, and speech recognition rates are adopted.

• Journal of Convergence for Information Technology
• /
• v.11 no.6
• /
• pp.33-39
• /
• 2021

Speech recognition technology is being combined with deep learning and is developing at a rapid pace. In particular, voice recognition services are connected to various devices such as artificial intelligence speakers, vehicle voice recognition, and smartphones, and voice recognition technology is being used in various places, not in specific areas of the industry. In this situation, research to meet high expectations for the technology is also being actively conducted. Among them, in the field of natural language processing (NLP), there is a need for research in the field of removing ambient noise or unnecessary voice signals that have a great influence on the speech recognition recognition rate. Many domestic and foreign companies are already using the latest AI technology for such research. Among them, research using a convolutional neural network algorithm (CNN) is being actively conducted. The purpose of this study is to determine the non-voice section from the user's speech section through the convolutional neural network. It collects the voice files (wav) of 5 speakers to generate learning data, and utilizes the convolutional neural network to determine the speech section and the non-voice section. A classification model for discriminating speech sections was created. Afterwards, an experiment was conducted to detect the non-speech section through the generated model, and as a result, an accuracy of 94% was obtained.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.3
• /
• pp.48-55
• /
• 2001

A novel method to reduce additive non-stationary noise is proposed. The method requires neither the information about noise nor the estimate of the noise statistics from any pause regions. The enhancement is performed on a band-by-band basis for each time frame. Based on both the decision on whether a particular band in a frame is speech or noise dominant and the masking property of the human auditory system, an appropriate amount of noise is reduced using spectral subtraction. The proposed method was tested on various noisy conditions (car noise, Fl6 noise, white Gaussian noise, pink noise, tank noise and babble noise) and on the basis of comparing segmental SNR with spectral subtraction method and visually inspecting the enhanced spectrograms and listening to the enhanced speech, the method was able to effectively reduce various noise while minimizing distortion to speech.