The application of machine learning techniques in bridge health monitoring is gaining widespread popularity as it overcomes the problems faced by conventional methods. However, the scarcity of labeled data for damaged...
详细信息
The application of machine learning techniques in bridge health monitoring is gaining widespread popularity as it overcomes the problems faced by conventional methods. However, the scarcity of labeled data for damaged bridges in training the model acts as a hindrance. The present study proposes a data science-based novel approach for overcoming this hindrance using a semisupervised, output-only method for multiple-level damage identification of a steel truss bridge. The method employs sequence-to-sequence modeling of vehicle-induced vibration response only from a single sensor position. The authors have used a bidirectional long short-term memory (BiLSTM) network for damage feature extraction. A statistical distance metric tool, Kullback-Leibler divergence, has then been utilized for feature discrimination. The method's efficiency is numerically investigated through a 3-D finite element model of a steel truss bridge based on real bridge specifications. A dynamic analysis using a moving vehicle is performed to obtain vehicle-induced accelerations. A total of 36 different damage scenarios have then been incorporated into the bridge. The effect of sensor position and performance because of variation in vehicle operation has also been investigated. The results show that the proposed approach successfully detects all the damage scenarios. The methodology's performance has also been validated in detecting damages for the Old ADA Bridge benchmark data. The methodology successfully detected multiple damage states using a single sensor response.
We propose a new paradigm for maintaining speaker identity in dysarthric voice conversion (DVC). The poor quality of dysarthric speech can be greatly improved by statistical VC, but as the normal speech utterances of ...
详细信息
ISBN:
(纸本)9781713836902
We propose a new paradigm for maintaining speaker identity in dysarthric voice conversion (DVC). The poor quality of dysarthric speech can be greatly improved by statistical VC, but as the normal speech utterances of a dysarthria patient are nearly impossible to collect, previous work failed to recover the individuality of the patient. In light of this, we suggest a novel, two-stage approach for DVC, which is highly flexible in that no normal speech of the patient is required. First, a powerful parallel sequence-to-sequence model converts the input dysarthric speech into a normal speech of a reference speaker as an intermediate product, and a nonparallel, frame-wise VC model realized with a variational autoencoder then converts the speaker identity of the reference speech back to that of the patient while assumed to be capable of preserving the enhanced quality. We investigate several design options. Experimental evaluation results demonstrate the potential of our approach to improving the quality of the dysarthric speech while maintaining the speaker identity.
This paper demonstrates the application of hierarchical convolutional neural networks using self-attention mechanisms for the task of generating recipes given a set of ingredients the recipe should contain. We compare...
详细信息
ISBN:
(纸本)9781665448901
This paper demonstrates the application of hierarchical convolutional neural networks using self-attention mechanisms for the task of generating recipes given a set of ingredients the recipe should contain. We compare this model, RECIPEGM, to an LSTM baseline and RecipeGPT using several metrics and show that our model is able to outperform even RecipeGPT in some cases. Furthermore, this work discusses suitable evaluation techniques for recipe generation and highlights weak points of some current in use metrics.
Analogies have been central to creative problem-solving throughout the history of science and technology. As the number of scientific articles continues to increase exponentially, there is a growing opportunity for fi...
详细信息
Analogies have been central to creative problem-solving throughout the history of science and technology. As the number of scientific articles continues to increase exponentially, there is a growing opportunity for finding diverse solutions to existing problems. However, realizing this potential requires the development of a means for searching through a large corpus that goes beyond surface matches and simple keywords. Here we contribute the first end-to-end system for analogical search on scientific articles and evaluate its effectiveness with scientists' own problems. Using a human-in-the-loop AI system as a probe we find that our system facilitates creative ideation, and that ideation success is mediated by an intermediate level of matching on the problem abstraction (i.e., high versus low). We also demonstrate a fully automated AI search engine that achieves a similar accuracy with the human-in-the-loop system. We conclude with design implications for enabling automated analogical inspiration engines to accelerate scientific innovation.
This paper presents a high quality singing synthesizer that is able to model a voice with limited available recordings. Based on the sequence-to-sequence singing model, we design a multi-singer framework to leverage a...
详细信息
ISBN:
(纸本)9781713820697
This paper presents a high quality singing synthesizer that is able to model a voice with limited available recordings. Based on the sequence-to-sequence singing model, we design a multi-singer framework to leverage all the existing singing data of different singers. To attenuate the issue of musical score unbalance among singers, we incorporate an adversarial task of singer classification to make encoder output less singer dependent. Furthermore, we apply multiple random window discriminators (MRWDs) on the generated acoustic features to make the network be a GAN. Both objective and subjective evaluations indicate that the proposed synthesizer can generate higher quality singing voice than baseline (4.12 vs 3.53 in MOS). Especially, the articulation of high-pitched vowels is significantly enhanced.
The proposed model unites the robustness of the extractive and abstractive summarization strategies. Three tasks indispensable to automatic summarization, namely, apprehension, extraction, and abstraction, are perform...
详细信息
ISBN:
(纸本)9783030446895;9783030446888
The proposed model unites the robustness of the extractive and abstractive summarization strategies. Three tasks indispensable to automatic summarization, namely, apprehension, extraction, and abstraction, are performed by two specially designed networks, the highlighter RNN and the generator RNN. While the highlighter RNN collectively performs the task of highlighting and extraction for identifying the salient facts in the input text, the generator RNN fabricates the summary based on those facts. The summary is generated using word-level extraction with the help of term-frequency inverse document frequency (TFIDF) ranking factor. The union of the two strategies proves to surpass the ROUGE score results on the Gigaword dataset as compared to the simple abstractive approach for summarization.
Interaction with machines using speech has been a popular research topic in recent years. Considerable amount of work focuses on the improvement of voice control systems which utilize automatic speech recognition(ASR)...
详细信息
Interaction with machines using speech has been a popular research topic in recent years. Considerable amount of work focuses on the improvement of voice control systems which utilize automatic speech recognition(ASR) and natural language processing(NLP) technologies to recognize user's speech and extract executable commands. The existing voice control systems usually do not take into count the diversity and richness of natural language and require users to follow pre-defined keywords or grammar rules. To address this limitation, we designed and implemented a voice control system that supports natural language, utilizing an attention-based command detection model. Our system supports flexible voice instructions and the user does not need to follow any pre-defined rules. An Arduino 4 WD robot car was also built in this paper to verify the system. In the experiments, the accuracy of command detection on natural language reaches 0.993 in our developed dataset. Besides, the realization of the 3-DOF(degree of freedom) motion control on our robot car suggests the feasibility of using our proposed system to control any functionality or behavior of the hardware system. Our work improves the flexibility and usability of voice control systems by applying technologies in the domain of NLP.
暂无评论