• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.33-36
• /
• 2007

In this paper, we investigate a fast speaker adaptation method based on eigenvoice in several noisy environments. In order to overcome its weakness against noise, we propose a noisy environment clustering method which divides the noisy adaptation utterances into utterance groups with similar environments by the vector quantization based clustering using a cepstral mean as a feature vector. Then each utterance group is used for adaptation to make an environment dependent model. According to our experiment, we obtained 19-37 % relative improvement in error rate compared with the simultaneous speaker adaptation and environmental compensation method

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.3
• /
• pp.45-50
• /
• 2000

This paper proposes a delta energy method based on Parameter Filtering(PF), which is a speech segmentation algorithm for text dependent speaker verification system over telephone line. Our parametric filter bank adopts a variable bandwidth along with a fixed center frequency. Comparing with other methods, the proposed method turns out very robust to channel noise and background noise. Using this method, we segment an utterance into consecutive subword units, and make models using each subword nit. In terms of EER, the speaker verification system based on whole word model represents 6.1%, whereas the speaker verification system based on subword model represents 4.0%, improving about 2% in EER.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.10a
• /
• pp.1021-1026
• /
• 2003

While multilayer perceptrons (MLPs) have great possibility on the application to speaker verification, they suffer from inferior learning speed. To appeal to users, the speaker verification systems based on MLPs must achieve a reasonable enrolling speed and it is thoroughly dependent on the fast teaming of MLPs. To attain real-time enrollment on the systems, the previous two studies have been devoted to the problem and each satisfied the objective. In this paper, the two studies are combined and applied to the systems, on the assumption that each method operates on different optimization principle. By conducting experiments using an MLP-based speaker verification system to which the combination is applied on real speech database, the feasibility of the combination is verified from the results of the experiments.

• Korean Journal of Materials Research
• /
• v.21 no.7
• /
• pp.403-409
• /
• 2011

Micro speakers are used to reproduce sound in small electric and information and communications devices, such as cellular phones, PMPs, and MP3 players. The acoustical properties and sound quality, which are changed due to the decreased size of the speaker, are often adjusted varying the type and thickness of the diaphragm. The most widely used diaphragm material is thin polymer. It was previously reported by the author of this paper that the resonance frequency of a micro speaker is changed by the type and thickness of a polymer diaphragm. In this paper, the frequency response near the resonance frequency of a micro speaker was studied as functions of the type and thickness of the polymer diaphragm. While $R_{max}$ and $R_{DC}$ were affected by the type and thickness, an analysis of the electrical impedance curve revealed that $R_o(= R_{max}/R_{DC})$ and ${\Delta}f$ were not changed. Thus, $Q_{TS}$ which was function of $R_o$, ${\Delta}f$, and the resonance frequency, is only related to the resonance frequency. The increase of the resonance frequency led to a proportional rise of $Q_{TS}$. The change of the frequency response near the resonance frequency was not dependent on the type or thickness of the polymer diaphragm, but was affected by the resonance frequency.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.2
• /
• pp.137-142
• /
• 2020

Many studies based on I-vector have been conducted in a variety of environments, from text-dependent short-utterance to text-independent long-utterance. In this paper, we propose a speaker verification system employing a combination of I-vector with Probabilistic Linear Discriminant Analysis (PLDA) and speaker embedding of Long Short Term Memory (LSTM) with attention mechanism in far-field and noisy environments. The LSTM model's Equal Error Rate (EER) is 15.52 % and the Attention-LSTM model is 8.46 %, improving by 7.06 %. We show that the proposed method solves the problem of the existing extraction process which defines embedding as a heuristic. The EER of the I-vector/PLDA without combining is 6.18 % that shows the best performance. And combined with attention-LSTM based embedding is 2.57 % that is 3.61 % less than the baseline system, and which improves performance by 58.41 %.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.673-680
• /
• 2003

In this paper, we study the enhancement of VQ (Vector Quantization) design for text independent speaker recognition. In a concrete way, we present a non-iterative method which makes a vector quantization codebook and this method performs non-iterative learning so that the computational complexity is epochally reduced The proposed Classified Space VQ (CSVQ) design method for text Independent speaker recognition is generalized from Semi-noniterative VQ design method for text dependent speaker recognition. CSVQ contrasts with the existing desiEn method which uses the iterative learninE algorithm for every traininE speaker. The characteristics of a CSVQ design is as follows. First, the proposed method performs the non-iterative learning by using a Classified Space Codebook. Second, a quantization region of each speaker is equivalent for the quantization region of a Classified Space Codebook. And the quantization point of each speaker is the optimal point for the statistical distribution of each speaker in a quantization region of a Classified Space Codebook. Third, Classified Space Codebook (CSC) is constructed through Sample Vector Formation Method (CSVQ1, 2) and Hyper-Lattice Formation Method (CSVQ 3). In the numerical experiment, we use the 12th met-cepstrum feature vectors of 10 speakers and compare it with the existing method, changing the codebook size from 16 to 128 for each Classified Space Codebook. The recognition rate of the proposed method is 100% for CSVQ1, 2. It is equal to the recognition rate of the existing method. Therefore the proposed CSVQ design method is, reducing computational complexity and maintaining the recognition rate, new alternative proposal and CSVQ with CSC can be applied to a general purpose recognition.

• The Journal of the Acoustical Society of Korea
• /
• v.6 no.3
• /
• pp.60-67
• /
• 1987

In this paper, a phoneme classification method for Korean speech recognition has been proposed and its performance has been studied. The phoneme classification has been done based on the phonemic features extracted by the prewindowed recursive least-square (PRLS) algorithm that is a kind of adaptive filter algorithms. Applying the PRLS algorithm to input speech signal, precise detection of phoneme boundaries has been made, Reference patterns of Korean phonemes have been generated by the ordinery vector quantization (VQ) of feature vectors obtained manualy from prototype regions of each phoneme. In order to obtain the performance of the proposed phoneme classification method, the method has been tested using spoken names of seven Korean cities which have eleven different consonants and eight different vowels. In the speaker-dependent phoneme classification, the accuracy is about $85\%$ considering simple phonemic rules of Korean language, while the accuracy of the speaker-independent case is far less than that of the speaker-dependent case.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.92-96
• /
• 2004

The researches of the emotions are currently great interest in speech processing as well as in human-machine interaction domain. In the recent years, more and more of researches relating to emotion synthesis or emotion recognition are developed for the different purposes. Each approach uses its methods and its various parameters measured on the speech signal. In this paper, we proposed using a short-time parameter: MFCC coefficients (Mel­Frequency Cepstrum Coefficients) and a simple but efficient classifying method: Vector Quantification (VQ) for speaker-dependent emotion recognition. Many other features: energy, pitch, zero crossing, phonetic rate, LPC... and their derivatives are also tested and combined with MFCC coefficients in order to find the best combination. The other models: GMM and HMM (Discrete and Continuous Hidden Markov Model) are studied as well in the hope that the usage of continuous distribution and the temporal behaviour of this set of features will improve the quality of emotion recognition. The maximum accuracy recognizing five different emotions exceeds $88\%$ by using only MFCC coefficients with VQ model. This is a simple but efficient approach, the result is even much better than those obtained with the same database in human evaluation by listening and judging without returning permission nor comparison between sentences [8]; And this result is positively comparable with the other approaches.

• ETRI Journal
• /
• v.32 no.3
• /
• pp.395-405
• /
• 2010

A novel multiclassifier system (MCS) strategy is proposed and applied to a text-dependent speaker verification task. The presented scheme optimizes the linear combination of classifiers on an on-line basis. In contrast to ordinary MCS approaches, neither a priori distributions nor pre-tuned parameters are required. The idea is to improve the most accurate classifier by making use of the incremental information provided by the second classifier. The on-line multiclassifier optimization approach is applicable to any pattern recognition problem. The proposed method needs neither a priori distributions nor pre-estimated weights, and does not make use of any consideration about training/testing matching conditions. Results with Yoho database show that the presented approach can lead to reductions in equal error rate as high as 28%, when compared with the most accurate classifier, and 11% against a standard method for the optimization of linear combination of classifiers.

• Journal of Information Technology Services
• /
• v.20 no.5
• /
• pp.43-54
• /
• 2021

Currently, citizens' expectations and concerns on utilizing artificial intelligence (AI) technologies in the public sector are widening with the rapid digital transformation. Furthermore the level of global acceptance on the AI and other intelligent digital technologies is augmenting with the needs of non-face-to-face types of public services more than ever due to the unforeseen and unpredictable pandemic, COVID-19. Thus, this study intended to empirically examine what policy directions for the public should be considered to provide well-designed services as well as to promote the evidence-based public policies in terms of Al speaker technology as a non-contact smart city service. Based on the survey of senior citizens' perceptions on AI (AI Speaker technology), this study conducted structure equation modeling analyses to identify whether technology acceptance models on to the varied dependent variables such as actual use, perception, attitude, and brand royalty. The Results of the empirical analyses showed that AI increased the positive level of citizens' perception, attitude and brand royalty on non-contact public services (smart city services) which are becoming more crucial for developing AI oriented government and providing intelligent public services effectively. In addition, theoretical and practical implications are discussed for understanding the changes of public service in the post-corona.