教学课程资源库 更多>>

关键词： Text-to-speech synthesis   Deep learning   Sequence-to-sequence model   End-to-end learning   Tacotron  

摘要： Neural sequence-to-sequence text-to-speech synthesis (TTS) can produce high-quality speech directly from text or simple linguistic features such as phonemes. Unlike traditional pipeline TTS, the neural sequence-to-sequence TTS does not require manually annotated and complicated linguistic features such as part-of-speech tags and syntactic structures for system training. However, it must be carefully designed and well optimized so that it can implicitly extract useful linguistic features from the input features. In this paper we investigate under what conditions the neural sequence-to-sequence TTS can work well in Japanese and English along with comparisons with deep neural network (DNN) based pipeline TTS systems. Unlike past comparative studies, the pipeline systems also use neural autoregressive (AR) probabilistic modeling and a neural vocoder in the same way as the sequence-to-sequence systems do for a fair and deep analysis in this paper. We investigated systems from three aspects: a) model architecture, b) model parameter size, and c) language. For the model architecture aspect, we adopt modified Tacotron systems that we previously proposed and their variants using an encoder from Tacotron or Tacotron2. For the model parameter size aspect, we investigate two model parameter sizes. For the language aspect, we conduct listening tests in both Japanese and English to see if our findings can be generalized across languages. Our experiments on Japanese demonstrated that the Tacotron TTS systems with increased parameter size and input of phonemes and accentual type labels outperformed the DNN-based pipeline systems using the complicated linguistic features and that its encoder could learn to compensate for a lack of rich linguistic features. Our experiments on English demonstrated that, when using a suitable encoder, the Tacotron TTS system with characters as input can disambiguate pronunciations and produce natural speech as good as those of the systems using phoneme

关键词： Semantics  

摘要： Linguistic steganalysis can indicate the existence of steganographic content in suspicious text carriers. Precise linguistic steganalysis on suspicious carrier is critical for multimedia security. In this paper, we introduced a neural linguistic steganalysis approach based on multi-head self-attention. In the proposed steganalysis approach, words in text are firstly mapped into semantic space with a hidden representation for better modeling the semantic features. Then, we utilize multi-head self-attention to model the interactions between words in carrier. Finally, a softmax layer is utilized to categorize the input text as cover or stego. Extensive experiments validate the effectiveness of our approach.

关键词： Second language   Reading   Literacy   Functional MRI   Print   speech convergence  

摘要： Parallel cohorts of Hebrew speakers learning English in the U.S., and American-English speakers learning Hebrew in Israel were tracked over the course of two years of immersion in their L2. We utilised a functional MRI semantic judgement task with print and speech tokens, as well as a battery of linguistic and cognitive behavioural measures prior to and after immersion, to track changes in both L1 and L2 processing. fMRI activation for print tokens produced a similar network of activation in both English and Hebrew, irrespective of L1 or L2 status. Significant convergence of print and speech processing was also observed in both languages across a network of left-hemisphere regions joint for both L1 and L2. Despite significant increases in behavioural measures of L2 proficiency, only a few signs of longitudinal change in L2 brain activation were found. In contrast, L1 showed widespread differences in processing across time, suggesting that the neurobiological footprint of reading is dynamic and plastic even in adults, with L2 immersion impacting L1 processing. Print/speech convergence showed little longitudinal change, suggesting that it is a stable marker of the differences in L1 and L2 processing across L2 proficiency.

关键词： Large-scale group decision-making   Bi-objective clustering   Evolutionary algorithm   Hesitant fuzzy linguistic preference relation  

摘要： Large-scale group decision-making process has received an increasing attention in recent years. After making the general survey of the existing large-scale group decision-making methods, we have found that: 1) consistency threshold value of hesitant fuzzy linguistic preference relation is fixed in traditional consistency measures;2) the clustering process of LSGDM does not consider the similar relationship between different evaluation information and the information quality simultaneously. Thus, in order to tackle the above issues and describe the hesitancy of experts in the decision-making process, the paper proposes a hesitant fuzzy linguistic bi-objective clustering method considering consensus and information entropy for tackling large-scale group decision-making problems. Firstly, a selection procedure for preference information is developed to quickly select suitable experts who meet the consistency requirements. Then, a bi-objective clustering method based on the group consensus degree indicator and group information entropy indicator is proposed to divide the experts into different clusters, considering the similar relationship and the quality of evaluation information simultaneously. After that, comprehensive preference information and the overall ranking of alternatives can be obtained. In the end, illustrative example of choosing the optimal way to protect the personal information while defending against COVID-19 and some comparative study show that the proposed method is valid for large-scale group decision-making problems and has good performance and strong robustness.

关键词： Group decision-making   Consensus thresholds   Linguistic preference relations   Consensus reaching process   Probabilistic linguistic sets  

摘要： When solving group decision-making (GDM) problems, the proper values of consensus thresholds are vital for consensus checking and improving. Decision makers are usually not confident to select a proper threshold. In the linguistic setting, this paper presents a new process to support the determination of consensus thresholds. A new concept, namely random consensus index, is presented to serve as a reference object so that the risk preference of a decision maker could be induced by comparing the quality of the information in hands with the averaging quality of randomly generated information. In this sense, admissible consensus thresholds could be determined automatically, and decision makers are not necessary to focus on the detail of consensus measures. Furthermore, the process is applied to the GDM problems with probabilistic linguistic preference relations, and a new GDM approach is presented. Different from the existing contributions, the consensus is measured by the probability of a set of preference relations being with acceptable consensus, and then the consensus is improved by revising the involved probability distributions. All the involved parameters are intuitive and interpretable. A case study, regarding the departure audit in China, demonstrates that the proposed GDM approach is effective even if the original preferences of experts are with low consistency and consensus.

关键词： 认知语言学   培训学校   词汇教学   教学策略   英语专业  

摘要： 词汇作为英语语言学习的基础,是学习英语中其他内容的基础和前提,只有掌握好英语词汇,才能够更好地掌握英语这门语言,从而提高英语学习成绩。我国英语培训学校在近些年来的发展速度十分迅猛,且与学校的英语教学方法有很大的不同,出现了以认知语言学为理论基础的英语词汇教学方法。本文对认知语言学下的培训学校英语词汇教学进行了深入的研究与分析,并提出了一些合理的教学策略,旨在进一步提高培训学校的英语教学水平。