• Speech Sciences
• /
• v.10 no.3
• /
• pp.225-239
• /
• 2003

In this paper, we develop a keyword spotting system using vocabulary-independent speech recognition technique, and investigate several non-keyword modeling and post-processing methods to improve its performance. In order to model non-keyword speech segments, monophone clustering and Gaussian Mixture Model (GMM) are considered. We employ likelihood ratio scoring method for the post-processing schemes to verify the recognition results, and filler models, anti-subword models and N-best decoding results are considered as an alternative hypothesis for likelihood ratio scoring. We also examine different methods to construct anti-subword models. We evaluate the performance of our system on the automatic telephone exchange service task. The results show that GMM-based non-keyword modeling yields better performance than that using monophone clustering. According to the post-processing experiment, the method using anti-keyword model based on Kullback-Leibler distance and N-best decoding method show better performance than other methods, and we could reduce more than 50% of keyword recognition errors with keyword rejection rate of 5%.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.3E
• /
• pp.19-23
• /
• 1997

The goal of postprocessing in automatic speech recognition is to improve recognition performance by utterance verification at the output of recognition stage. It is focused on the effective rejection of out-of vocabulary words based on the confidence score of hypothesized candidate word. We present two methods for computing confidence scores. Both methods are based on the distance between each observation vector and the representative code vector, which is defined by the most likely code vector at each state. While the first method employs simple time normalization, the second one uses a normalization technique based on the concept of on-line garbage mode[1]. According to the speaker independent isolated words recognition experiment with discrete density HMM, the second method outperforms both the first one and conventional likelihood ratio scoring method[2].

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.5
• /
• pp.13-19
• /
• 2000

The blind segmentation method, which segments input speech data into recognition unit without any prior knowledge, plays an important role in continuous speech recognition system and corpus generation. As no prior knowledge is required, this method is rather simple to implement, but in general, it suffers from bad performance when compared to the knowledge-based segmentation method. In this paper, we introduce a method to improve the performance of a blind segmentation of Korean continuous speech by postprocessing the segment boundaries obtained from the blind segmentation. In the preprocessing stage, the candidate boundaries are extracted by a clustering technique based on the GLR(generalized likelihood ratio) distance measure. In the postprocessing stage, the final phoneme boundaries are selected from the candidates by utilizing a simple a priori knowledge on the syllabic structure of Korean, i.e., the maximum number of phonemes between any consecutive nuclei is limited. The experimental result was rather promising : the proposed method yields 25% reduction of insertion error rate compared that of the blind segmentation alone.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.4
• /
• pp.65-77
• /
• 1999

There are two problems which will be processed to graft a continuous speech recognition results into natural language processing technique. First, the speaking's unit isn't consistent with text's spacing unit. Second, when it is to be pronounced the phonological alternation phenomena occur inside morphemes or among morphemes. In this paper, we implement the postprocessing system of a continuous speech recognition that above all, solve two problems using the eo-jeol generator and syllable recoveror and morphologically analyze the generated results and then correct the failed results through the corrector. Our system experiments with two kinds of speech corpus, i.e., a primary school text book and editorial corpus. The successful percentage of the former is 93.72%, that of the latter is 92.26%. As results of experiment, we verified that our system is stable regardless the sorts of corpus.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.7
• /
• pp.46-55
• /
• 1999

We proposed the new method of postprocessing which not only reduces the frequency of dictionary access using morphological analysis but improve the recognition rate of character recognizer. In this paper, after estimating morphological construction of mis-recognized word using the part of speech that is analyzed, correct presumed mis-recognized morphology. The postprocessing using a morphology unit reduce candidate because of short than word and frequency of dictionary access because there is no need to morphological analysis for candidate. To select right candidate is only necessary to dictionary access. The proposed results show that reduced the frequency of dictionary access to 60% than postprocessing method using a word unit and recognition rate improved from 94% to 97%.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.5
• /
• pp.44-50
• /
• 1995

This paper describes a large-vocabulary continuous speech recognition system using continuous hidden Markov models for the Korean language. To improve the performance of the system, we study on the selection of speech modeling units, inter-word modeling, search algorithm, and grammars. We used triphones as basic speech modeling units, generalized triphones and function word-dependent phones are used to improve the trainability of speech units and to reduce errors in function words. Silence between words is optionally inserted by using a silence model and a null transition. Word pair grammar and bigram model based oil word classes are used. Also we implement a search algorithm to find N-best candidate sentences. A postprocessor reorders the N-best sentences using word triple grammar, selects the most likely sentence as the final recognition result, and finally corrects trivial errors related with postpositions. In recognition tests using a 3,000-word continuous speech database, the system attained $93.1\%$ word recognition accuracy and $73.8\%$ sentence recognition accuracy using word triple grammar in postprocessing.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.2
• /
• pp.280-286
• /
• 2013

In this paper, a noise reduction system is proposed for the speech interface in intelligent TV applications. To reduce TV speaker sound which are very serious noises degrading recognition performance, a noise reduction algorithm utilizing the direct TV sound as the reference noise input is implemented. In the proposed algorithm, transfer functions are estimated to compensate for the difference between the direct TV sound and that recorded with the microphone installed on the TV frame. Then, the noise power spectrum in the received signal is calculated to perform Wiener filter-based noise cancellation. Additionally, a postprocessing step is applied to reduce remaining noises. Experimental results show that the proposed algorithm shows 88% recognition rate for isolated Korean words at 5 dB input SNR.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.6
• /
• pp.106-109
• /
• 1997

For the practical isolated word recognition system, the ability to reject the out-of -vocabulary(OOV) is required. In this paper, we present a rejection method which uses the clustered phoneme modeling combined with postprocessing by likelihood ratio scoring. Our baseline speech recognition system was based on the whole-word continuous HMM. And 6 clustered phoneme models were generated using statistical method from the 45 context independent phoneme models, which were trained using the phonetically balanced speech database. The test of the rejection performance for speaker independent isolated words recogntion task on the 22 section names shows that our method is superior to the conventional postprocessing method, performing the rejection according to the likelihood difference between the first and second candidates. Furthermore, this clustered phoneme models do not require retraining for the other isolated word recognition system with different vocabulary sets.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.8
• /
• pp.726-734
• /
• 2007

Generally, a mobile robot is moved by original input programs. However, it is very hard for a non-expert to change the program generating the moving path of a mobile robot, because he doesn't know almost the teaching command and operating method for driving the robot. Therefore, the teaching method with speech command for a handicapped person without hands or a non-expert without an expert knowledge to generate the path is required gradually. In this study, for easily teaching the moving path of the autonomous mobile robot, the autonomous mobile robot with the function of speech recognition is developed. The use of human voice as the teaching method provides more convenient user-interface for mobile robot. To implement the teaching function, the designed robot system is composed of three separated control modules, which are speech preprocessing module, DC servo motor control module, and main control module. In this study, we design and implement a speaker dependent isolated word recognition system for creating moving path of an autonomous mobile robot in the unknown environment. The system uses word-level Hidden Markov Models(HMM) for designated command vocabularies to control a mobile robot, and it has postprocessing by neural network according to the condition based on confidence score. As the spectral analysis method, we use a filter-bank analysis model to extract of features of the voice. The proposed word recognition system is tested using 33 Korean words for control of the mobile robot navigation, and we also evaluate the performance of navigation of a mobile robot using only voice command.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.10
• /
• pp.25-33
• /
• 2012

In this paper, we propose a rule-based model to correct errors in a speech recognition result in the mobile device environment. The proposed model considers the mobile device environment with limited resources such as processing time and memory, as follows. In order to minimize the error correction processing time, the proposed model removes some processing steps such as morphological analysis and the composition and decomposition of syllable. Also, the proposed model utilizes the longest match rule selection method to generate one error correction candidate per point, assumed that an error occurs. For the purpose of deploying memory resource, the proposed model uses neither the Eojeol dictionary nor the morphological analyzer, and stores a combined rule list without any classification. Considering the modification and maintenance of the proposed model, the error correction rules are automatically extracted from a training corpus. Experimental results show that the proposed model improves 5.27% on the precision and 5.60% on the recall based on Eojoel unit for the speech recognition result.