• Phonetics and Speech Sciences
• /
• v.1 no.3
• /
• pp.109-115
• /
• 2009

Many isolated word recognition systems may generate non-similar words for recognition candidates because they use only acoustic information. In this paper, we investigate several techniques which can exclude non-similar words from N-best candidate words by applying Levenstein distance measure. At first, word distance method based on phone and syllable distances are considered. These methods use just Levenstein distance on phones or double Levenstein distance algorithm on syllables of candidates. Next, word similarity approaches are presented that they use characters' position information of word candidates. Each character's position is labeled to inserted, deleted, and correct position after alignment between source and target string. The word similarities are obtained from characters' positional probabilities which mean the frequency ratio of the same characters' observations on the position. From experimental results, we can find that the proposed methods are effective for removing non-similar words without loss of system performance from the N-best recognition candidates of the systems.

• Phonetics and Speech Sciences
• /
• v.2 no.4
• /
• pp.153-161
• /
• 2010

Many isolated word recognition systems may generate non-similar words for recognition candidates because they use only acoustic information. The previous study [1,2] investigated several techniques which can exclude non-similar words from N-best candidate words by applying Levenstein distance measure. This paper discusses the various improving techniques of removing non-similar recognition results. The mentioned methods include comparison penalties or weights, phone accuracy based on confusion information, weights candidates by ranking order and partial comparisons. Through experimental results, it is found that some proposed method keeps more accurate recognition results than the previous method's results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.2
• /
• pp.389-405
• /
• 2014

Outdated Channel State Information (CSI) was proved to have negative effect on performance in two-way relay networks. The diversity order of widely used opportunistic relay selection (ORS) was degraded to unity in networks with outdated CSI. This paper proposed a multiple relay selection scheme for amplify-and-forward (AF) based two-way relay networks (TWRN) with outdated CSI. In this scheme, two sources exchange information through more than one relays. We firstly select N best relays out of all candidate relays with respect to signal-noise ratio (SNR). Then, the ratios of the SNRs on the rest of the candidate relays to that of the Nth highest SNR are tested against a normalized threshold ${\mu}{\in}[0,1]$, and only those relays passing this test are selected in addition to the N best relays. Expressions of outage probability, average bit error rate (BER) and ergodic channel capacity were obtained in closed-form for the proposed scheme. Numerical results and Simulations verified our theoretical analyses, and showed that the proposed scheme had significant gains comparing with conventional ORS.

• The Plant Pathology Journal
• /
• v.32 no.1
• /
• pp.33-46
• /
• 2016

In this study, the full-length nucleotide sequences of four Iranian PVY isolates belonging to $PVY^N$ strain were determined. The genome of Iranian PVY isolates were 9,703-9,707 nucleotides long encoding all potyviral cistrons including P1, HC-Pro, P3, 6K1, CI, 6K2, VPg, NIa-Pro, NIb and CP with coding regions of 825, 1,395, 1,095, 156, 1,902, 156, 564, 732, 1,557 and 801 nucleotides in length, respectively. The length of pipo, embedded in the P3 cistron, was 231 nucleotides. Phylogenetic analysis showed that the Iranian isolates clustered with European recombinant NTN isolates in the N lineage. Recombination analysis demonstrated that Iranian $PVY^N$ isolates had a typical European $PVY^{NTN}$ genome having three recombinant junctions while $PVY^N$ and $PVY^O$ were identified as the parents. We used dN/dS methods to detect candidate amino acid positions for positive selection in viral proteins. The mean ${\omega}$ ratio differed among different genes. Using model M0, ${\omega}$ values were 0.267 (P1), 0.085 (HC-Pro), 0.153 (P3), 0.050 (CI), 0.078 (VPg), 0.087 (NIa-pro), 0.079 (NIb) and 0.165 (CP). The analysis showed different sites within P1, P3 and CP were under positive selection pressure, however, the sites varied among PVY populations. To the best of our knowledge, our analysis provides the first demonstration of population structure of $PVY^N$ strain in mid-Eurasia Iran using complete genome sequences and highlights the importance of recombination and selection pressure in the evolution of PVY.

• Journal of Korean Institute of Industrial Engineers
• /
• v.18 no.2
• /
• pp.141-147
• /
• 1992

This article evaluates the efficiency of three branch-and-bound heuristics for a job scheduling problem that minimizes the sum of absolute deviations of completion times from a common due date. To improve the performance of the branch-and-bound procedure, Algorithm SA is presented for the initial feasible schedule and three heuristics : breadth-first, depth-first and best-first search are investigated depending on the candidate selection procedure. For the three heuristics the CPU time, memory space, and the number of nodes generated are computed and tested with nine small examples (6 ${\leq}$ n ${\leq}$ 4). Medium sized random problems (10 ${\leq}$ n ${\leq}$ 30) are also generated and examined. The computational results are compared and discussed for the three heuristics.

• 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.