Search

Speech imagery recognition from electroencephalograms (EEGs) could potentially become a strong contender among non-invasive brain-computer interfaces (BCIs). In this report, first we extract language representations as the difference of line-spectra of phones by statistically analyzing many EEG signals from the Broca area. Then we extract vowels by using iterative search from hand-labeled short-syllable data. The iterative search process consists of principal component analysis (PCA) that visualizes linguistic representation of vowels through eigen-vectors φ(m), and subspace method (SM) that searches an optimum line-spectrum for redesigning φ(m). The extracted linguistic representation of Japanese vowels /i/ /e/ /a/ /o/ /u/ shows 2 distinguished spectral peaks (P1, P2) in the upper frequency range. The 5 vowels are aligned on the P1-P2 chart. A 5-vowel recognition experiment using a data set of 5 subjects and a convolutional neural network (CNN) classifier gave a mean accuracy rate of 72.6%.

The precise conversion of arbitrary text into its corresponding phoneme sequence (grapheme-to-phoneme or G2P conversion) is implemented in speech synthesis and recognition, pronunciation learning software, spoken term detection and spoken document retrieval systems. Because the quality of this module plays an important role in the performance of such systems and many problems regarding G2P conversion have been reported, we propose a novel two-stage model-based approach, which is implemented using an existing weighted finite-state transducer-based G2P conversion framework, to improve the performance of the G2P conversion model. The first-stage model is built for automatic conversion of words to phonemes, while the second-stage model utilizes the input graphemes and output phonemes obtained from the first stage to determine the best final output phoneme sequence. Additionally, we designed new grapheme generation rules, which enable extra detail for the vowel and consonant graphemes appearing within a word. When compared with previous approaches, the evaluation results indicate that our approach using rules focusing on the vowel graphemes slightly improved the accuracy of the out-of-vocabulary dataset and consistently increased the accuracy of the in-vocabulary dataset.

To develop a new fertilizing system with a reduced amount of phosphatic fertilizer in sweet corn production, we applied potassium phosphate to the plug seedlings before transplanting to the field, and examined its effects on growth, yield, photosynthetic activity and absorption of minerals. The amount of phosphatic and potash fertilizers necessary to grow sweet corn could be reduced by the pre-transplanting KP application (PTKPA) to the plug seedlings. We considered the mechanisms involved in the reduction of P and K application rate by PTKPA as follows; 1) PTKPA increased the P content of plant, which accelerated the root establishment. 2) The advanced root establishment not only reduced the duration of water stress, but also increased absorption of the essential nutrients such as N and Mg. 3) Higher content of N and Mg led to higher chlorophyll content and possibly protein content, which activated photosynthesis during the early growth stage. 4) Improved photosynthetic activities increased NAR during the early growth stage. 5) This increase in NAR accelerated leaf expansion, increasing LAI. 6) Larger LAI during the early growth stage led to larger LAI throughout the growing stage, resulting in a higher CGR and ear yield.