期刊： COMPUTER SPEECH AND LANGUAGE, 2021; 68 ()
The pharyngeal fricative is a typical compensatory articulation disorder in cleft palate speech. It is produced by retracting the root of the tongue t......
期刊： COMPUTER SPEECH AND LANGUAGE, 2021; 68 ()
Global vectors, or global embeddings, are important word representations for many natural language processing tasks. With the popularity of dynamic em......
期刊： COMPUTER SPEECH AND LANGUAGE, 2021; 68 ()
Intuitively, image-or video-based recommendations seem to be more reliable than those containing plain text, and these types of recommendations have r......
期刊： COMPUTER SPEECH AND LANGUAGE, 2021; 68 ()
Far -field speech processing is an important and challenging problem. In this paper, we propose deep ad-hoc beamforming, a deep-learning-based multich......
期刊： COMPUTER SPEECH AND LANGUAGE, 2021; 70 ()
Text-to-Speech (TTS) synthesis plays an important role in human-computer interaction. Currently, most TTS technologies focus on the naturalness of spe......
期刊： COMPUTER SPEECH AND LANGUAGE, 2021; 68 ()
Short text is the main carrier for people to express their ideas and opinions. And it is very important as well a big challenge to understand the mean......
期刊： COMPUTER SPEECH AND LANGUAGE, 2021; 68 ()
Neural networks have been widely used in the field of text classification, and have achieved good results on various Chinese datasets. However, for lo......
期刊： COMPUTER SPEECH AND LANGUAGE, 2021; 70 ()
Generative Adversarial Nets (GAN) has been successfully introduced to unconditional generating text to alleviate exposure bias. However, the discrimin......
期刊： COMPUTER SPEECH AND LANGUAGE, 2021; 66 ()
Query-based document summarization aims to extract or generate a summary of a document which directly answers or is relevant to the search query. It i......
期刊： COMPUTER SPEECH AND LANGUAGE, 2021; 66 ()
Existing methods for question answering over knowledge bases (KBQA) ignore the consideration of the model prediction uncertainties. We argue that esti......
期刊： COMPUTER SPEECH AND LANGUAGE, 2021; 66 ()
Neural network methods which leverage word-embedding obtained from unsupervised learning models have been widely adopted in many natural language proc......
期刊： COMPUTER SPEECH AND LANGUAGE, 2021; 66 ()
Replay attacks pose the most severe threat to automatic speaker verification systems among various spoofing attacks. In this paper, we propose a novel......
期刊： COMPUTER SPEECH AND LANGUAGE, 2021; 67 ()
Visual storytelling is a creative and challenging task, aiming to automatically generate a story-like description for a sequence of images. The descri......
期刊： COMPUTER SPEECH AND LANGUAGE, 2021; 67 ()
Generating structured query language (SQL) from natural language is an emerging research topic. This paper presents a new learning paradigm from indir......
期刊： COMPUTER SPEECH AND LANGUAGE, 2021; 68 ()
Text generation with auxiliary attributes, such as topics or sentiments, has made remarkable progress. However, high-quality labeled data is difficult......
