188 resultados para Mandarin
Resumo:
We propose that a general analytic framework for cultural science can be constructed as a generalization of the generic micro meso macro framework proposed by Dopfer and Potts (2008). This paper outlines this argument along with some implications for the creative industries research agenda.
Resumo:
Brown spot (caused by Alternaria alternata) is a major disease of citrus in subtropical areas of Australia. A number of chemicals, the strobilurins azoxystrobin, trifloxystrobin, pyraclostrobin and methoxycrylate, a plant activator (acibenzolar), copper hydroxide, mancozeb, captan, iprodione and chlorothalonil/pyrimthanil were tested in the field for its control. Over three seasons, trees in a commercial orchard received 16, 14 and 7 fungicide sprays, respectively, commencing at flowering in the first season, and petal fall in the later seasons. In all experiments, the strobilurins used alone, or incorporated with copper and mancozeb, were as effective as, or better than the industry standard of copper and mancozeb alone. The only exception was trifloxystrobin, which when used alone was less effective than the industry standard. Acibenzolar used alone was ineffective. Applying a mixture of azoxystrobin and acibenzolar was found to reduce the incidence of brown spot compared with applying azoxystrobin alone but, in either case, disease levels were not found to be significantly different to the industry standard. Captan, iprodione and chlorothalonil/pyrimthanil were as effective as the industry standard. The incidence and severity of rind damage were significantly lowest in the azoxystrobin, methoxycrylate, iprodione and chlorothalonil/pyrimthanil treatments. Medium and high rates of trifloxystrobin (0.07 g/L, 0 .15 g/L) and pyraclostrobin (0.8 g/L, 1.2 g/L) applied alone were the only treatments found to be IPM-incompatible as shown by the elevated level of scale infection on fruit.
Resumo:
The utility of near infrared spectroscopy as a non-invasive technique for the assessment of internal eating quality parameters of mandarin fruit (Citrus reticulata cv. Imperial) was assessed. The calibration procedure for the attributes of TSS (total soluble solids) and DM (dry matter) was optimised with respect to a reference sampling technique, scan averaging, spectral window, data pre-treatment (in terms of derivative treatment and scatter correction routine) and regression procedure. The recommended procedure involved sampling of an equatorial position on the fruit with 1 scan per spectrum, and modified partial least squares model development on a 720–950-nm window, pre-treated as first derivative absorbance data (gap size of 4 data points) with standard normal variance and detrend scatter correction. Calibration model performance for the attributes of TSS and DM content was encouraging (typical Rc2 of >0.75 and 0.90, respectively; typical root mean squared standard error of calibration of <0.4 and 0.6%, respectively), whereas that for juiciness and total acidity was unacceptable. The robustness of the TSS and DM calibrations across new populations of fruit is documented in a companion study.
Resumo:
The robustness of multivariate calibration models, based on near infrared spectroscopy, for the assessment of total soluble solids (TSS) and dry matter (DM) of intact mandarin fruit (Citrus reticulata cv. Imperial) was assessed. TSS calibration model performance was validated in terms of prediction of populations of fruit not in the original population (different harvest days from a single tree, different harvest localities, different harvest seasons). Of these, calibration performance was most affected by validation across seasons (signal to noise statistic on root mean squared error of prediction of 3.8, compared with 20 and 13 for locality and harvest day, respectively). Procedures for sample selection from the validation population for addition to the calibration population (‘model updating’) were considered for both TSS and DM models. Random selection from the validation group worked as well as more sophisticated selection procedures, with approximately 20 samples required. Models that were developed using samples at a range of temperatures were robust in validation for TSS and DM.
Resumo:
Imperial mandarin is the dominant variety in the early season production time slot in Australia. It is well known to consumers, wholesalers and supermarkets, and growers continue to make new plantings of this variety. Despite this popularity, Imperial has major faults that cause problems for growers, consumers, and at other points along the supply chain. Fruit of the variety can be severely granulated, and this is the main quality problem cited by consumers. A second problem with Imperial is its unsuitability for export. Thirdly, the variety has low juice and sugar content, and develops poor colour under warm conditions. We propose a hybridisation project to specifically address these industry obstacles.
Resumo:
A significant cost in obtaining acoustic training data is the generation of accurate transcriptions. For some sources close-caption data is available. This allows the use of lightly-supervised training techniques. However, for some sources and languages close-caption is not available. In these cases unsupervised training techniques must be used. This paper examines the use of unsupervised techniques for discriminative training. In unsupervised training automatic transcriptions from a recognition system are used for training. As these transcriptions may be errorful data selection may be useful. Two forms of selection are described, one to remove non-target language shows, the other to remove segments with low confidence. Experiments were carried out on a Mandarin transcriptions task. Two types of test data were considered, Broadcast News (BN) and Broadcast Conversations (BC). Results show that the gains from unsupervised discriminative training are highly dependent on the accuracy of the automatic transcriptions. © 2007 IEEE.
Discriminative language model adaptation for Mandarin broadcast speech transcription and translation
Resumo:
This paper investigates unsupervised test-time adaptation of language models (LM) using discriminative methods for a Mandarin broadcast speech transcription and translation task. A standard approach to adapt interpolated language models to is to optimize the component weights by minimizing the perplexity on supervision data. This is a widely made approximation for language modeling in automatic speech recognition (ASR) systems. For speech translation tasks, it is unclear whether a strong correlation still exists between perplexity and various forms of error cost functions in recognition and translation stages. The proposed minimum Bayes risk (MBR) based approach provides a flexible framework for unsupervised LM adaptation. It generalizes to a variety of forms of recognition and translation error metrics. LM adaptation is performed at the audio document level using either the character error rate (CER), or translation edit rate (TER) as the cost function. An efficient parameter estimation scheme using the extended Baum-Welch (EBW) algorithm is proposed. Experimental results on a state-of-the-art speech recognition and translation system are presented. The MBR adapted language models gave the best recognition and translation performance and reduced the TER score by up to 0.54% absolute. © 2007 IEEE.
Resumo:
This paper describes the development of the CU-HTK Mandarin Speech-To-Text (STT) system and assesses its performance as part of a transcription-translation pipeline which converts broadcast Mandarin audio into English text. Recent improvements to the STT system are described and these give Character Error Rate (CER) gains of 14.3% absolute for a Broadcast Conversation (BC) task and 5.1% absolute for a Broadcast News (BN) task. The output of these STT systems is then post-processed, so that it consists of sentence-like segments, and translated into English text using a Statistical Machine Translation (SMT) system. The performance of the transcription-translation pipeline is evaluated using the Translation Edit Rate (TER) and BLEU metrics. It is shown that improving both the STT system and the post-STT segmentations can lower the TER scores by up to 5.3% absolute and increase the BLEU scores by up to 2.7% absolute. © 2007 IEEE.
Resumo:
This paper discusses the development of the CU-HTK Mandarin Broadcast News (BN) transcription system. The Mandarin BN task includes a significant amount of English data. Hence techniques have been investigated to allow the same system to handle both Mandarin and English by augmenting the Mandarin training sets with English acoustic and language model training data. A range of acoustic models were built including models based on Gaussianised features, speaker adaptive training and feature-space MPE. A multi-branch system architecture is described in which multiple acoustic model types, alternate phone sets and segmentations can be used in a system combination framework to generate the final output. The final system shows state-of-the-art performance over a range of test sets. ©2006 British Crown Copyright.
Discriminative language model adaptation for Mandarin broadcast speech transcription and translation