Open Test Set Research Articles

MFAMNet: Multi-Scale Feature Attention Mixture Network for Short-Term Load Forecasting

Short-term load forecasting is an important prerequisite for smart grid controls. The current methods are mainly based on the convolution neural network (CNN) or long short-term memory (LSTM) model to realize load forecasting. For the multi-factor input sequence, the existing methods cannot obtain multi-scale features of the time series and the important parameters of the multi-factor, resulting in low accuracy and robustness. To address these problems, a multi-scale feature attention hybrid network is proposed, which uses LSTM to extract the time correlation of the sequence and multi-scale CNN to automatically extract the multi-scale feature of the load. This work realizes the integration of features by constructing a circular network. In the proposed model, a two-branch attention mechanism is further constructed to capture the important parameters of different influencing factors to improve the model’s robustness, which can make the network to obtain effective features at the curve changes. Comparative experiments on two open test sets show that the proposed multi-scale feature attention mixture network can achieve accurate short-term load forecasting and is superior to the existing methods.

Acteve++: An Improved Android Application Automatic Tester Based on Acteve

As the Android application increases in number, it is a challenge for researchers to test Android applications automatically. Acteve based on dynamic symbolic execution proposes a new method and achieves higher coverage. But it cannot achieve the ideal test coverage due to incomplete events input and some missing activities. In this paper, we propose an improvement scheme, making Acteve can produce broadcast events as test inputs, and has the capability to find more activities. Based on these improved schemes, we design Android applications automatic tester, Acteve ++. We experimented and analyzed existing representative Android automated testing tools: Monkey , Dynodroid , GUIRipper , Acteve , and Acteve ++ on an open test set. The experiments show that Acteve ++ achieves high average test coverage in an acceptable time.

Improving Myanmar Automatic Speech Recognition with Optimization of Convolutional Neural Network Parameters

Researchers of many nations have developed automatic speech recognition (ASR) to show their national improvement in information and communication technology for their languages. This work intends to improve the ASR performance for Myanmar language by changing different Convolutional Neural Network (CNN) hyperparameters such as number of feature maps and pooling size. CNN has the abilities of reducing in spectral variations and modeling spectral correlations that exist in the signal due to the locality and pooling operation. Therefore, the impact of the hyperparameters on CNN accuracy in ASR tasks is investigated. A 42-hr-data set is used as training data and the ASR performance was evaluated on two open test sets: web news and recorded data. As Myanmar language is a syllable-timed language, ASR based on syllable was built and compared with ASR based on word. As the result, it gained 16.7% word error rate (WER) and 11.5% syllable error rate (SER) on TestSet1. And it also achieved 21.83% WER and 15.76% SER on TestSet2.

IMPROVING MYANMAR AUTOMATIC SPEECH RECOGNITION WITH OPTIMIZATION OF CONVOLUTIONAL NEURAL NETWORK PARAMETERS

Researchers of many nations have developed automatic speech recognition (ASR) to show their national improvement in information and communication technology for their languages. This work intends to improve the ASR performance for Myanmar language by changing different Convolutional Neural Network (CNN) hyperparameters such as number of feature maps and pooling size. CNN has the abilities of reducing in spectral variations and modeling spectral correlations that exist in the signal due to the locality and pooling operation. Therefore, the impact of the hyperparameters on CNN accuracy in ASR tasks is investigated. A 42-hr-data set is used as training data and the ASR performance was evaluated on two open test sets: web news and recorded data. As Myanmar language is a syllable-timed language, ASR based on syllable was built and compared with ASR based on word. As the result, it gained 16.7% word error rate (WER) and 11.5% syllable error rate (SER) on TestSet1. And it also achieved 21.83% WER and 15.76% SER on TestSet2.

An integration method of multiple search results for spoken term detection

We propose a new integration method of multiple search results for improving search accuracy of Spoken Term Detection (STD). A usual STD system prepares two types of recognition results of spoken documents. If a query consists of in-vocabulary (IV) terms, the results using word-based recognizer are used, and if a query includes out-of-vocabulary (OOV) terms, the results using subword-based recognizer are used. The paper proposes an integration method of these two search results. Each utterance has a similarity score included in the search results. The scores of two results for an utterance has been integrated linearly using a constant weighting factor so far. Our preliminary experiments showed the search accuracy using the subword-based results was higher for some IV queries. In the same way, that using the word-based results was higher for some OOV queries. In the proposed method, the similarity scores of the two search results are compared for the same utterance and a higher weighing factor is given to the results that showed a higher similarity score. The proposed method is evaluated using open test sets, and experimental results demonstrated the search accuracy improved for all test sets.

Stem-Affix based Uyghur Morphological Analyzer

Uyghur language is an agglutinative language in which words are derived from stems (or roots) by concatenating suffixes. This property makes a large number of combinations of morphemes, and greatly increases the word-vocabulary size, causing out-of-vocabulary (OOV) and data sparseness problems for statistical models. So words are split into certain sub-word units and applied to text and speech processing applications. Proper sub-word units not only provide high coverage and smaller lexicon size, but also provide semantic and syntactic information which is necessary for downstream applications. This paper discusses a general purpose morphological analyzer tool which can split a text of words into sequence of morphemes or syllables. Uyghur morpheme segmentation is a basic part of the comprehensive effort of the Uyghur language corpus compilation. As there are no delimiters for sub-word units, a supervised method, combined with certain rules and a statistical learning algorithm, is applied for morpheme segmentation. For phonetic units like syllable and phonemes, pure rule-based methods can extract with high accuracy. Most common and proper sub-words for various applications can be the linguistic morphemes for they provide linguistic information, high coverage, low lexicon size, and easily be restored to words. As the Uyghur language is written as pronounced, phonetic alterations of speech are openly expressed in text. This property makes many surface forms for a particular morpheme. A general purpose morphological analyzer must be able to analyze and export in both standard and surface forms. So the morphophonetic alterations like phonetic harmony, weakening, and morphological changes are summarized and learnt from training corpus. And a statistical model based morpheme segmentation tool is trained on the corpus of aligned word-morpheme sequences, and applied to predict possible morpheme sequences. For an open test set, with word coverage of 86.8% and morpheme coverage of 98.4%, the morpheme segmentation accuracy is 97.6%. This morpheme segmentation tool can output both on the standard forms and on the surface forms without costing segmentation accuracy. Furthermore, for various basic lexical units of word, morpheme, and syllable, the statistical properties are compared as a comprehensive effort of the Uyghur language corpus compilation.

Improved Neural Machine Translation with SMT Features

Neural machine translation (NMT) conducts end-to-end translation with a source language encoder and a target language decoder, making promising translation performance. However, as a newly emerged approach, the method has some limitations. An NMT system usually has to apply a vocabulary of certain size to avoid the time-consuming training and decoding, thus it causes a serious out-of-vocabulary problem. Furthermore, the decoder lacks a mechanism to guarantee all the source words to be translated and usually favors short translations, resulting in fluent but inadequate translations. In order to solve the above problems, we incorporate statistical machine translation (SMT) features, such as a translation model and an n-gram language model, with the NMT model under the log-linear framework. Our experiments show that the proposed method significantly improves the translation quality of the state-ofthe-art NMT system on Chinese-to-English translation tasks. Our method produces a gain of up to 2.33 BLEU score on NIST open test sets.

Training Set Selection for Building Compact and Efficient Language Models

For statistical language model training, target domain matched corpora are required. However, training corpora sometimes include both target domain matched and unmatched sentences. In such a case, training set selection is effective for both reducing model size and improving model performance. In this paper, training set selection method for statistical language model training is described. The method provides two advantages for training a language model. One is its capacity to improve the language model performance, and the other is its capacity to reduce computational loads for the language model. The method has four steps. 1) Sentence clustering is applied to all available corpora. 2) Language models are trained on each cluster. 3) Perplexity on the development set is calculated using the language models. 4) For the final language model training, we use the clusters whose language models yield low perplexities. The experimental results indicate that the language model trained on the data selected by our method gives lower perplexity on an open test set than a language model trained on all available corpora.

Minimum error classification training of HMMs-Implementation details and experimental results.

This paper describes an implementation of minimum error training for continuous gaussian mixture density HMMs. Instead of maximising the conditional probability of producing a set of training data, as in the conventional HMM maximum likelihood approach, we train to minimise the number of recognition errors. The most important aspect of this work is the use of a first order differentiable “loss” function, the minimisation of which is directly related to the minimisation of the recognition error rate. The performance of the resulting minimum error HMMs was compared against that of conventional maximum likelihood HMMs in a continuous speech recognition task using the ATR 5, 240 Japanese word data base. The results were impressive. For example, for 10 mixture 5 state Baum-Welch trained HMMs, after minimum error training word error rates reduced from 20.6% to 3.0% on the closed training set and 23.2% to 13.2% on the open test set. Furthermore, 3 mixture minimum error HMMs performed better than 10 mixture maximum likelihood HMMs. In fact in every performance measure made the minimum error HMMs proved to be superior.