• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.541-544
• /
• 2021

본 논문은 어떤 기업의 주식 주문 정보를 담고 있는 호가창(limit order book)과 해당 기업과 관련된 뉴스 헤드라인을 사용하여 해당 기업의 주가 등락을 예측하는 딥러닝 기반 모델을 제안한다. 제안 모델은 호가창의 중기 변화와 단기 변화를 모두 고려하는 한편, 동기간 발생한 뉴스 헤드라인까지 예측에 고려함으로써 주가 등락 예측 정확도를 높인다. 제안 모델은 호가창의 변화의 특징을 CNN(convolutional neural network)으로 추출하고 뉴스 헤드라인을 Word2vec으로 생성된 단어 임베딩 벡터를 사용하여 나타낸 뒤, 이들 정보를 결합하여 특정 기업 주식의 다음 날 등락여부를 예측한다. NASDAQ 실데이터를 사용한 실험을 통해 제안 모델로 5개 종목(Amazon, Apple, Facebook, Google, Tesla)의 일일 주가 등락을 예측한 결과, 제안 모델은 기존 방법에 비해 정확도를 최대 17.14%, 평균 10.7% 향상시켰다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.351-352
• /
• 2023

본 논문은 과거 한국 가요(K 팝)의 가사를 수집하여 (1) 특정 키워드와 관련된 기존 가사를 검색하거나, (2) 작사가가 작성한 새로운 가사와 유사한 기존 가사를 검색하거나, (3) 특정 키워드와 관련된 가사 속 어휘를 제안하는 작사 지원 시스템을 제안한다. 지금까지의 음악 관련 시스템은 음악을 소비하는 사람들을 위한 음악 추천 시스템에 집중해 왔으나, 이 연구에서는 음악을 생산하는 작사가에게 초점을 맞춰 이들을 돕는 작사 지원 시스템을 제안하고자 한다. 제안 시스템은 TF-IDF 와 word2vec 을 활용하여 가사와 단어 벡터 공간에 가사와 어휘를 배치하고 코사인 유사도를 계산한다.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.3
• /
• pp.56-62
• /
• 2001

In this paper, we adopt a missing data theory to speech recognition. It can be used in order to maintain high performance of speech recognizer when the missing data occurs. In general, hidden Markov model (HMM) is used as a stochastic classifier for speech recognition task. Acoustic events are represented by continuous probability density function in continuous density HMM(CDHMM). The missing data theory has an advantage that can be easily applicable to this CDHMM. A marginalization method is used for processing missing data because it has small complexity and is easy to apply to automatic speech recognition (ASR). Also, a spectral subtraction is used for detecting missing data. If the difference between the energy of speech and that of background noise is below given threshold value, we determine that missing has occurred. We propose a new method that examines the reliability of detected missing data using voicing probability. The voicing probability is used to find voiced frames. It is used to process the missing data in voiced region that has more redundant information than consonants. The experimental results showed that our method improves performance than baseline system that uses spectral subtraction method only. In 452 words isolated word recognition experiment, the proposed method using the voicing probability reduced the average word error rate by 12％ in a typical noise situation.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.2E
• /
• pp.58-67
• /
• 1994

Hidden Markov Model (HMM)-based algorithms have been used successfully in many speech recognition systems, especially large vocabulary systems. Although general purpose processors can be employed for the system, they inevitably suffer from the computational complexity and enormous data. Therefore, it is essential for real-time speech recognition to develop specialized hardware to accelerate the recognition steps. This paper concerns with a real-time implementation of an isolated word recognition system based on HMM. The speech recognition system consists of a host computer (PC), a DSP board, and a prototype Viterbi scoring board. The DSP board extracts feature vectors of speech signal. The Viterbi scoring board has been implemented using three field-programmable gate array chips. It employs a hardware-efficient Viterbi scoring architecture and performs the Viterbi algorithm for HMM-based speech recognition. At the clock rate of 10 MHz, the system can update about 100,000 states within a single frame of 10ms.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.1
• /
• pp.48-53
• /
• 2003

Eigenvoice method is known to be adequate for fast speaker adaptation, but it hardly shows additional improvement with increased amount of adaptation data. In this paper, to deal with this problem, we propose a modified method estimating the weights of eigenvoices in each feature vector dimension. We also propose an adaptation mode selection scheme that one method with higher performance among several adaptation methods is selected according to the amount of adaptation data. We used POW DB to construct the speaker independent model and eigenvoices, and utterances(ranging from 1 to 50) from PBW 452 DB and the remaining 400 utterances were used for adaptation and evaluation, respectively. With the increased amount of adaptation data, proposed dimensional eigenvoice method showed higher performance than both conventional eigenvoice method and MLLR. Up to 26% of word error rate was reduced by the adaptation mode selection between eigenvoice and dimensional eigenvoice methods in comparison with conventional eigenvoice method.

• Journal of Digital Convergence
• /
• v.14 no.8
• /
• pp.233-243
• /
• 2016

Due to speech recognition problems in noisy environment, Audio Visual Speech Recognition (AVSR) system, which combines speech information and visual information, has been proposed since the mid-1990s,. and lip reading have played significant role in the AVSR System. This study aims to enhance recognition rate of utterance word using only lip shape detection for efficient AVSR system. After preprocessing for lip region detection, Convolution Neural Network (CNN) techniques are applied for utterance period detection and lip shape feature vector extraction, and Hidden Markov Models (HMMs) are then used for the recognition. As a result, the utterance period detection results show 91% of success rates, which are higher performance than general threshold methods. In the lip reading recognition, while user-dependent experiment records 88.5%, user-independent experiment shows 80.2% of recognition rates, which are improved results compared to the previous studies.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.9
• /
• pp.103-112
• /
• 1999

In this paper, a speaker-independent isolated world recognition system for a car navigation system is implemented using a general digital signal processor. This paper presents a method combining SNR normalization with RAS as a noise processing method. The semi-continuous hidden markov model is adopted and TMS320C31 is used in implementing the real-time system. Recognition word set is composed of 69 command words for a car navigation system. Experimental results showed that the recognition performance has a maximum of 93.62% in case of a combination of SNR normalization and spectral subtraction, and the performance improvement rate of the system is 3.69%, Presented noise processing method showed good speech recognition performance in 5dB SNR in car environment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.2
• /
• pp.423-428
• /
• 2017

These days, various and tons of education information are rapidly increasing and spreading due to Internet and smart devices usage. Recently, as e-Learning usage increasing, many instructors and students (learners) need to set a goal to maximize learners' result of education and education system efficiency based on big data analytics via online recorded education historical data. In this paper, the author applied Word2Vec algorithm (neural network algorithm) to find similarity among education words and classification by clustering algorithm in order to objectively recognize and analyze online recorded education historical data. When the author applied the Word2Vec algorithm to education words, related-meaning words can be found, classified and get a similar vector values via learning repetition. In addition, through experimental results, the author proved the part of speech (noun, verb, adjective and adverb) have same shortest distance from the centroid by using clustering algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.11
• /
• pp.1505-1511
• /
• 2021

Pretrained models with high performance in various tasks within natural language processing have the advantage of learning the linguistic patterns of sentences using large corpus during the training, allowing each token in the input sentence to be represented with appropriate feature vectors. One of the methods of constructing a corpus required for a pre-trained model training is a collection method using web crawler. However, sentences that exist on web may contain unnecessary words in some or all of the sentences because they have various patterns. In this paper, we propose a dataset construction method for filtering sentences containing unnecessary words using neural network models for corpus collected from the web. As a result, we construct a dataset containing a total of 2,330 sentences. We also evaluated the performance of neural network models on the constructed dataset, and the BERT model showed the highest performance with an accuracy of 93.75%.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.127-146
• /
• 2022

Recently, as word embedding has shown excellent performance in various tasks of deep learning-based natural language processing, researches on the advancement and application of word, sentence, and document embedding are being actively conducted. Among them, cross-language transfer, which enables semantic exchange between different languages, is growing simultaneously with the development of embedding models. Academia's interests in vector alignment are growing with the expectation that it can be applied to various embedding-based analysis. In particular, vector alignment is expected to be applied to mapping between specialized domains and generalized domains. In other words, it is expected that it will be possible to map the vocabulary of specialized fields such as R&D, medicine, and law into the space of the pre-trained language model learned with huge volume of general-purpose documents, or provide a clue for mapping vocabulary between mutually different specialized fields. However, since linear-based vector alignment which has been mainly studied in academia basically assumes statistical linearity, it tends to simplify the vector space. This essentially assumes that different types of vector spaces are geometrically similar, which yields a limitation that it causes inevitable distortion in the alignment process. To overcome this limitation, we propose a deep learning-based vector alignment methodology that effectively learns the nonlinearity of data. The proposed methodology consists of sequential learning of a skip-connected autoencoder and a regression model to align the specialized word embedding expressed in each space to the general embedding space. Finally, through the inference of the two trained models, the specialized vocabulary can be aligned in the general space. To verify the performance of the proposed methodology, an experiment was performed on a total of 77,578 documents in the field of 'health care' among national R&D tasks performed from 2011 to 2020. As a result, it was confirmed that the proposed methodology showed superior performance in terms of cosine similarity compared to the existing linear vector alignment.