• Journal of Digital Forensics
• /
• v.13 no.1
• /
• pp.35-44
• /
• 2019

The voice-phishing is done by inducing victims to send money, only with voice through the personal information illegally obtained. The amount of damage caused by voice-phishing continues to increase every year, and it became a social problem. Recently, the Financial Supervisory Service (i.e. the FSS) in Republic of Korea has been collecting the voices of voice-phishing scamer from victims. In this paper, we describe an effective forensic speaker analysis method for detecting the voice from the same person compared with the large-scale speech files stored in database(DB), and apply the aforementioned forensic speaker analysis method with the collected voice-phising speech files from victims. At first, an i-vector of each speech file had been extracted from the DB, then, the cosine similarity matrix for the all speech files had been generated through the cosine distance among the extracted the i-vectors of all speech file in DB. In other words, it performed the speaker analysis as grouping a set of candidates with high common similarity among i-vectors of all speech files in DB. As a result of EER(Error Equal Rate) measurement for 6,724 speech files composed of 82 speakers, it was confirmed that the EER of the i-vector-based method is improved than that of the GMM-based method. Finally, as a result of comparing the collected 2,327 voice-phishing speech files collected by the FSS, it was shown that some of the speech files having similar voice features were grouped each other.

• The KIPS Transactions:PartB
• /
• v.15B no.1
• /
• pp.53-60
• /
• 2008

This paper proposes a new multiobjective optimization method for discriminative training of hidden Markov models (HMMs) used as the recognizer for automatic lipreading. While the conventional Baum-Welch algorithm for training HMMs aims at maximizing the probability of the data of a class from the corresponding HMM, we define a new training criterion composed of two minimization objectives and develop a global optimization method of the criterion based on simulated annealing. The result of a speaker-dependent recognition experiment shows that the proposed method improves performance by the relative error reduction rate of about 8% in comparison to the Baum-Welch algorithm.

• Phonetics and Speech Sciences
• /
• v.7 no.3
• /
• pp.131-138
• /
• 2015

In this paper, we propose L1-norm regularization for state vector adaptation of subspace Gaussian mixture model (SGMM). When you design a speaker adaptation system with GMM-HMM acoustic model, MAP is the most typical technique to be considered. However, in MAP adaptation procedure, large number of parameters should be updated simultaneously. We can adopt sparse adaptation such as L1-norm regularization or sparse MAP to cope with that, but the performance of sparse adaptation is not good as MAP adaptation. However, SGMM does not suffer a lot from sparse adaptation as GMM-HMM because each Gaussian mean vector in SGMM is defined as a weighted sum of basis vectors, which is much robust to the fluctuation of parameters. Since there are only a few adaptation techniques appropriate for SGMM, our proposed method could be powerful especially when the number of adaptation data is limited. Experimental results show that error reduction rate of the proposed method is better than the result of MAP adaptation of SGMM, even with small adaptation data.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.5
• /
• pp.213-221
• /
• 2006

Phone segmentation of speech waveform is especially important for concatenative text to speech synthesis which uses segmented corpora for the construction of synthetic units. because the quality of synthesized speech depends critically on the accuracy of the segmentation. In the beginning. the phone segmentation was manually performed. but it brings the huge effort and the large time delay. HMM-based approaches adopted from automatic speech recognition are most widely used for automatic segmentation in speech synthesis, providing a consistent and accurate phone labeling scheme. Even the HMM-based approach has been successful, it may locate a phone boundary at a different position than expected. In this paper. we categorized adjacent phoneme pairs and analyzed the mismatches between hand-labeled transcriptions and HMM-based labels. Then we described the dominant error patterns that must be improved for the speech synthesis. For the experiment. hand labeled standard Korean speech DB from ETRI was used as a reference DB. Time difference larger than 20ms between hand-labeled phoneme boundary and auto-aligned boundary is treated as an automatic segmentation error. Our experimental results from female speaker revealed that plosive-vowel, affricate-vowel and vowel-liquid pairs showed high accuracies, 99%, 99.5% and 99% respectively. But stop-nasal, stop-liquid and nasal-liquid pairs showed very low accuracies, 45%, 50% and 55%. And these from male speaker revealed similar tendency.

• Journal of Advanced Information Technology and Convergence
• /
• v.10 no.2
• /
• pp.49-59
• /
• 2020

As technologies have been developing, our lives are getting easier. Today we are surrounded by the new technologies such as AI and IoT. Moreover, the word, "smart" is a very broad one because we are trying to change our daily environment into smart one by using those technologies. For example, the traditional workplaces have changed into smart offices. Since the 3rd industrial revolution, we have used the touch interface to operate the machines. In the 4th industrial revolution, however, we are trying adding the speech recognition module to the machines to operate them by giving voice commands. Today many of the things are communicated with human by voice commands. Many of them are called AI things and they do tasks which users request and do tasks more than what users request. In the 4th industrial revolution, we use smartphones all the time every day from the morning to the night. For this reason, the privacy using phone is not guaranteed sometimes. For example, the caller's voice can be heard through the phone speaker when accepting a call. So, it is needed to protect privacy on smartphone and it should work automatically according to the user context. In this aspect, this paper proposes a method to adjust the voice volume for call to protect privacy on smartphone according to the user context.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.6
• /
• pp.5-14
• /
• 1994

This paper is about an experiment of speaker-independent automatic Korean spoken words recognition using Multi-Layered Perceptron and Error Back-propagation algorithm. The object words are 50 citynames of D.D.D local numbers. 43 of those are 2 syllables and the rest 7 are 3 syllables. The words were not segmented into syllables or phonemes, and some feature components extracted from the words in equal gap were applied to the neural network. That led independent result on the speech duration, and the PARCOR coefficients calculated from the frames using linear predictive analysis were employed as feature components. This paper tried to find out the optimum conditions through 4 differerent experiments which are comparison between total and pre-classified training, dependency of recognition rate on the number of frames and PAROCR order, recognition change due to the number of neurons in the hidden layer, and the comparison of the output pattern composition method of output neurons. As a result, the recognition rate of $89.6\%$ is obtaimed through the research.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.6
• /
• pp.277-281
• /
• 2006

This paper presents a method for the automatic recognition of pitch accents over syllables. The method that we propose is based on the time-delay recursive neural network (TDRNN). which is a neural network classifier with two different representation of dynamic context: the delayed input nodes allow the representation of an explicit trajectory F0(t) along time. while the recursive nodes provide long-term context information that reflects the characteristics of pitch accentuation in spoken English. We apply the TDRNN to pitch accent recognition in two forms: in the normal TDRNN. all of the prosodic features (pitch. energy, duration) are used as an entire set in a single TDRNN. while in the distributed TDRNN. the network consists of several TDRNNs each taking a single prosodic feature as the input. The final output of the distributed TDRNN is weighted sum of the output of individual TDRNN. We used the Boston Radio News Corpus (BRNC) for the experiments on the speaker-independent pitch accent recognition. π 1e experimental results show that the distributed TDRNN exhibits an average recognition accuracy of 83.64% over both pitch events and non-events.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.5
• /
• pp.105-114
• /
• 2000

In this paper, we concentrate on an efficient method to decrease a lot of pixel data to be processed with an Image transform based automatic lipreading It is reported that the image transform based approach, which obtains a compressed representation of the speaker's mouth, results in superior lipreading performance than the lip contour based approach But this approach produces so many feature parameters of the lip that has much data and requires much computation time for recognition To reduce the data to be computed, we propose a simple method folding at the vertical center of the lip-image based on the symmetry of the lip In addition, the principal component analysis(PCA) is used for fast algorithm and HMM word recognition results are reported The proposed method reduces the number of the feature parameters at $22{\sim}47%$ and improves hidden Markov model(HMM)word recognition rates at $2{\sim}3%$, using the folded lip-image compared with the normal method using $16{\times}16$ lip-image.

• Proceedings of the KSPS conference
• /
• 1996.10a
• /
• pp.53-69
• /
• 1996

Much research has been done on the rues differentiating the three Korean stops in word initial position. This paper focuses on a more neglected area: the acoustic cues differentiating the medial tense and lax unaspirated stops. Eight adult Korean native speakers, four males and four females, pronounced sixteen minimal pairs containing the two series of medial stops with different preceding vowel qualities. The average duration of vowels before lax stops is 31 msec longer than before their tense counterparts (70 msec for lax vs 39 msec for tense). In addition, the average duration of the stop closure of tense stops is 135 msec longer than that of lax stops (69 msec for lax vs 204msec for tense). THESE DURATIONAL DIFFERENCES ARE 50 LARGE THAT THEY MAY BE PHONOLOGICALLY DETERMINED, NOT PHONETICALLY. Moreover, vowel duration varies with the speaker's sex. Female speakers have 5 msec shorter vowel duration before both stops. The quality of voicing, tense or lax, is also a cue to these two stop types, as it is in initial position, but the relative duration of the stops appears to be much more important cues. The duration of stops changes the stop perception while that of preceding vowel does not. The consequences of these results for the phonological description of Korean as well as the synthesis and automatic recognition of Korean will be discussed.

• Journal of Satellite, Information and Communications
• /
• v.12 no.1
• /
• pp.101-106
• /
• 2017

In this paper, we present Emergency exit signs are installed to provide escape routes or ways in buildings like shopping malls, hospitals, industry, and government complex, etc. and various other places for safety purpose to aid people to escape easily during emergency situations. In case of an emergency situation like smoke, fire, bad lightings and crowded stamped condition at emergency situations, it's difficult for people to recognize the emergency exit signs and emergency doors to exit from the emergency building areas. This paper propose an automatic emergency exit sing recognition to find exit direction using a smart device. The proposed approach aims to develop an computer vision based smart phone application to detect emergency exit signs using the smart device camera and guide the direction to escape in the visible and audible output format. In this research, a CAMShift object tracking approach is used to detect the emergency exit sign and the direction information extracted using template matching method. The direction information of the exit sign is stored in a text format and then using text-to-speech the text synthesized to audible acoustic signal. The synthesized acoustic signal render on smart device speaker as an escape guide information to the user. This research result is analyzed and concluded from the views of visual elements selecting, EXIT appearance design and EXIT's placement in the building, which is very valuable and can be commonly referred in wayfinder system.