• The Journal of the Acoustical Society of Korea
• /
• v.22 no.3
• /
• pp.194-201
• /
• 2003

In speech recognition, confidence measuring is to decide whether it can be accepted as the recognized results or not. The confidence is measured by integrating frames into phone and word level. In case of word recognition, the confidence measuring verifies the results of recognition and Out-Of-Vocabulary (OOV). Therefore, the post-processing could improve the performance of recognizer without accepting it as a recognition error. In this paper, we measure the confidence modifying log likelihood ratio (LLR) which was the previous confidence measuring. It accumulates only those which the log likelihood ratio is negative when integrating the confidence to phone level from frame level. When comparing the verification performance for the results of word recognizer with the previous method, the FAR (False Acceptance Ratio) is decreased about 3.49% for the OOV and 15.25% for the recognition error when CAR (Correct Acceptance Ratio) is about 90%.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.5
• /
• pp.410-419
• /
• 2004

In this paper. we propose a method of confidence measure fusion under Bayesian framework for speech recognition. Centralized and distributed schemes are considered for confidence measure fusion. Centralized fusion is feature level fusion which combines the values of individual confidence scores and makes a final decision. In contrast. distributed fusion is decision level fusion which combines the individual decision makings made by each individual confidence measuring method. Optimal Bayesian fusion rules for centralized and distributed cases are presented. In isolated word Out-of-Vocabulary (OOV) rejection experiments. centralized Bayesian fusion shows over 13% relative equal error rate (EER) reduction compared with the individual confidence measure methods. In contrast. the distributed Bayesian fusion shows no significant performance increase.

• Annual Conference on Human and Language Technology
• /
• 2014.10a
• /
• pp.3-8
• /
• 2014

대화형 개인 비서 시스템은 사람의 음성을 통해 인식된 음성 인식 결과를 분석하여 사용자에게 제공할 정보가 무엇인지 파악한 후, 정보가 포함되어 있는 앱(app)을 실행시켜 사용자가 원하는 정보를 제공하는 시스템이다. 이러한 대화형 개인 비서 시스템의 가장 중요한 모듈 중 하나는 음성 대화 인식 모듈(SLU: Spoken Language Understanding)이며, 발화의 "의미 분석"을 수행하는 모듈이다. 본 논문은 음성 인식결과가 잘못되어 의미 분석이 실패하는 것을 방지하기 위하여 음성 인식 결과에서 잘못 인식된 명사, 개체명 단어를 보정 시켜주는 미등록어(OOV:Out-of-vocabulary) 처리 모듈을 제안한다. 제안하는 미등록어 처리 모듈은 미등록어 탐색 모듈과 미등록어 변환 모듈로 구성되며, 미등록어 탐색 모듈을 통해 사용자의 발화에서 미등록어를 분류하고, 미등록어 변환 모듈을 통해 미등록어를 사전에 존재하는 유사한 단어로 변환하는 방법을 제안한다. 제안한 방법을 적용하였을 때의 실험 결과, 전체 미등록어 중 최대 52.5%가 올바르게 수정되었으며, 음성 인식 결과를 그대로 사용했을 경우 "원본 문장"과 문장 단위 67.6%의 일치율을 보인 것에 반해 미등록어 처리 모듈을 적용했을 때 17.4% 개선된 최대 85%의 문장 단위 일치율을 보였다.

• Journal of Korea Multimedia Society
• /
• v.11 no.11
• /
• pp.1471-1479
• /
• 2008

In this paper, we propose a technique to improve Out-Of-Vocabulary(OOV) rejection algorithms in variable vocabulary recognition system which is much used in ASR(Automatic Speech Recognition). The rejection system can be classified into two categories by their implementation method, keyword spotting method and utterance verification method. The utterance verification method uses the likelihood ratio of each phoneme Viterbi score relative to anti-phoneme score for deciding OOV. In this paper, we add speaker verification system before utterance verification and calculate an speaker verification probability. The obtained speaker verification probability is applied for determining the proposed variable-confidence threshold. Using the proposed method, we achieve the significant performance improvement; CA(Correctly Accepted for keyword) 94.23%, CR(Correctly Rejected for out-of-vocabulary) 95.11% in office environment, and CA 91.14%, CR 92.74% in noisy environment.

• Journal of the Korea Convergence Society
• /
• v.12 no.3
• /
• pp.1-7
• /
• 2021

Since Neural Machine Translation (NMT) uses only a limited number of words, there is a possibility that words that are not registered in the dictionary will be entered as input. The proposed method to alleviate this Out of Vocabulary (OOV) problem is Subword Tokenization, which is a methodology for constructing words by dividing sentences into subword units smaller than words. In this paper, we deal with general subword tokenization algorithms. Furthermore, in order to create a vocabulary that can handle the infinite conjugation of Korean adjectives and verbs, we propose a new methodology for subword tokenization training by separating the Jongsung(coda) from Korean syllables (consisting of Chosung-onset, Jungsung-neucleus and Jongsung-coda). As a result of the experiment, the methodology proposed in this paper outperforms the existing subword tokenization methodology.

• MALSORI
• /
• no.51
• /
• pp.99-115
• /
• 2004

In this parer, we propose LM adaptation for broadcast news recognition. We collect information of recent articles from the internet on real time, make a recent small size LM, and then interpolate recent LM with a existing LM composed of existing large broadcast news corpus. We performed interpolation experiments to get the best type of articles from recent corpus because collected recent corpus is composed of articles which are related with test set, and which are unrelated. When we made an adapted LM using recent LM with similar articles to test set through Tf-Idf method and existing LM, we got the best result that ERR of pseudo-morpheme based recognition performance has 17.2 % improvement and the number of OOV has reduction from 70 to 27.

• Speech Sciences
• /
• v.10 no.2
• /
• pp.15-25
• /
• 2003

In this paper, we propose an algorithm on OOV(Out-of-Vocabulary) rejection based on two-stage method. In the first stage, the algorithm rejects OOVs using generic word model, and then in the second stage, for further reduction of false acceptance, it rejects words which have low similarity to the candidate by measuring the distance between HMM models. For the experiment, we choose 20 in-vocabulary words out of PBW445 DB distributed by ETRI. In case that the first stage is processed only, the false acceptance is 3% with 100% correct acceptance, and in case both stages are processed, the false acceptance is reduced to 1% with 100% correct acceptance.

• MALSORI
• /
• no.67
• /
• pp.149-166
• /
• 2008

In spoken document retrievals (SDR), subword (typically phonemes) indexing term is used to avoid the out-of-vocabulary (OOV) problem. It makes the indexing and retrieval process independent from any vocabulary. It also requires a small corpus to train the acoustic model. However, subword indexing term approach has a major drawback. It shows higher word error rates than the large vocabulary continuous speech recognition (LVCSR) system. In this paper, we propose an probabilistic slot detection and n-gram based string matching method for phone based spoken document retrievals to overcome high error rates of phone recognizer. Experimental results have shown 9.25% relative improvement in the mean average precision (mAP) with 1.7 times speed up in comparison with the baseline system.

• MALSORI
• /
• no.45
• /
• pp.79-91
• /
• 2003

Utterance verification aims at rejecting both out-of-vocabulary (OOV) utterances and low-confidence-scored in-vocabulary (IV) utterances. For utterance verification on Korean connected digit recognition task, we investigate several methods to construct filler and anti-digit models. In particular, we propose a substitution error correction method based on 2-best decoding results. In this method, when 1st candidate is rejected, 2nd candidate is selected if it is accepted by a specific hypothesis test, instead of simply rejecting the 1st one. Experimental results show that the proposed method outperforms the conventional log likelihood ratio (LLR) test method.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.111-114
• /
• 2002

음성인식에서 발화검증은 비인식대상어휘(OOV)를 기각시키고, 인식대상어휘라도 오인식 가능성이 높은 결과를 기각시키는 기술을 말한다. 본 논문에서는 혼동가능성 높은 숫자쌍들이 존재하는 한국어 연결 숫자 인식에서 발화검증 결과로 숫자열 기각시 오인식 가능성이 높은 숫자열을 그냥 기각시키는 대신에 대체오류를 수정하여 인식성능을 향상시키고자 하였다. N-best decoding 결과에 따르면 $2^{nd}\;best$ 나 $3^{rd}\;best$안에 대부분의 제대로 된 인식결과들이 포함된다. 따라서, N-best decoding을 이용해, 숫자열 기각시 $2^{nd}\;best$ 숫자열로 대체된 것이라고 가정한 후, 개별숫자 log likelihood ratio(LLR)과 N-best 기반의 숫자열 LLR[3] 등을 함께 고려한 신뢰도 측정방식에 의해 그 가정이 맞다고 판단이 되면 $2^{nd}\;best$ 의 숫자열과 대체함으로써 부분적으로 오류를 수정하였다.