• 말소리와 음성과학
• /
• 제1권3호
• /
• 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.

• 한국음향학회지
• /
• 제30권8호
• /
• pp.428-435
• /
• 2011

Many isolated word recognition systems may generate irrelevant words for recognition results because they use only acoustic information or small amount of language information. In this paper, I propose word similarity that is used for selecting (or removing) less common words from candidates by applying Levenshtein distance. Word similarity is obtained by using positional accuracy that reflects the frequency information along to character's alignment information. This paper also discusses various improving techniques of selection of disparate words. The methods include different loss values, phone accuracy based on confusion information, weights of candidates by ranking order and partial comparisons. Through experiments, I found that the proposed methods are effective for removing heterogeneous words without loss of performance.

• 말소리와 음성과학
• /
• 제2권4호
• /
• 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.

• Asian-Australasian Journal of Animal Sciences
• /
• 제25권3호
• /
• pp.299-303
• /
• 2012

Inbreeding is the mating of relatives that produce progeny having more homozygous alleles than non-inbred animals. Inbreeding increases numbers of recessive alleles, which is often associated with decreased performance known as inbreeding depression. The magnitude of inbreeding depression depends on the level of inbreeding in the animal. Level of inbreeding is expressed by the inbreeding coefficient. One breeding goal in livestock is uniform productivity while maintaining acceptable inbreeding levels, especially keeping inbreeding less than 20%. However, in closed herds without the introduction of new genetic sources high levels of inbreeding over time are unavoidable. One method that increases selection response and minimizes inbreeding is selection of individuals by weighting estimated breeding values with average relationships among individuals. Optimum genetic contribution theory (OGC) uses relationships among individuals as weighting factors. The algorithm is as follows: i) Identify the individual having the best EBV; ii) Calculate average relationships ($\bar{r_j}$) between selected and candidates; iii) Select the individual having the best EBV adjusted for average relationships using the weighting factor k, $EBV^*=EBV_j(1-k\bar{{r}_j})$ Repeat process until the number of individuals selected equals number required. The objective of this study was to compare simulated results based on OGC selection under different conditions over 30 generations. Individuals (n = 110) were generated for the base population with pseudo random numbers of N~ (0, 3), ten were assumed male, and the remainder female. Each male was mated to ten females, and every female was assumed to have 5 progeny resulting in 500 individuals in the following generation. Results showed the OGC algorithm effectively controlled inbreeding and maintained consistent increases in selection response. Difference in breeding values between selection with OGC algorithm and by EBV only was 8%, however, rate of inbreeding was controlled by 47% after 20 generation. These results indicate that the OGC algorithm can be used effectively in long-term selection programs.