Search

Voice information processing technology is developing rapidly under the impetus of deep learning.The combination of speech synthesis and voice conversion technology can achieve real-time high-fidelity voice output of designated objects and content,and has broad application prospects in man-machine interaction,pan-entertainment and other fields.This paper aims to provide an overview of speech synthesis and voice conversion technology based on deep learning.First,this paper briefly reviews the development of speech synthesis and voice conversion technology.Next,it enumerates the common public datasets in these fields so that it is convenient for researchers to carry out related explorations.Then,it discusses the TTS models,including the classic and cutting-edge models and algorithms in terms of style,rhythm,speed,and compares their effects and development potentials respectively.Then,it reviews voice conversion by summarizing the voice conversion methods and optimization methods.Finally,it summarizes the applications and challenges of speech synthesis and voice conversion,and looks forward to their future development direction in model compression,few-shot learning and forgery detection,based on the problems faced by them in terms of model,application and regulation.

Sentence ranking is the issue of most concern in document summarization today. While traditional feature-based approaches evaluate sentence significance and rank the sentences relying on the features that are particularly designed to characterize the different aspects of the individual sentences, the newly emerging graph-based ranking algorithms (such as the PageRank-like algorithms) recursively compute sentence significance using the global information in a text graph that links sentences together. In general, the existing PageRank-like algorithms can model well the phenomena that a sentence is important if it is linked by many other important sentences. Or they are capable of modeling the mutual reinforcement among the sentences in the text graph. However, when dealing with multidocument summarization these algorithms often assemble a set of documents into one large file. The document dimension is totally ignored. In this article we present a framework to model the two-level mutual reinforcement among sentences as well as documents. Under this framework we design and develop a novel ranking algorithm such that the document reinforcement is taken into account in the process of sentence ranking. The convergence issue is examined. We also explore an interesting and important property of the proposed algorithm. When evaluated on the DUC 2005 and 2006 query-oriented multidocument summarization datasets, significant results are achieved. [ABSTRACT FROM AUTHOR]

Abstract: Ethnopharmacological relevance: Desmodium podocarpum is a plant that has been used in the folk medicine to treat febrile diseases, cough and bleeding wounds. However, there is no scientific basis or reports in the modern literature regarding its effectiveness as an analgesic, anti-inflammatory and antipyretic agent. Aims of the study: The objective of this study is to evaluate the analgesic, anti-inflammatory and antipyretic activities of the petroleum ether fraction (PEF) from the ethanol extract of Desmodium podocarpum. Materials and methods: PEF (50, 100, 200mg/kg) was estimated for its pharmacological properties by using the acetic acid-induced writhing test, the hot plate test, the Carrageenan-induced rat paw edema model, the dimethylbenzene-induced mouse inflammation model, and the lipopolysaccharide (LPS)-induced rat fever model. In addition, the acute toxicity of PEF was also studied. Results: PEF significantly and dose-dependently inhibited the writhing responses in mice, increased reaction time of mice in the hot plate test, reduced carrageenan-induced paw edema in rats and the dimethylbenzene-induced ear edema in mice, and attenuated LPS-induced fever in rats. No death of mice was observed when orally administered PEF up to 4.2g/kg. Conclusions: These findings suggest that PEF possesses evident analgesic, anti-inflammatory and antipyretic activities, and has a favorable safety, which supports the use of Desmodium podocarpum as an analgesic, anti-inflammatory and antipyretic drug in the folk medicine. [Copyright &y& Elsevier]

Ethnopharmacological relevance: The root of Acanthopanax senticosus (also called Eleutherococcus senticosus or Siberian ginseng) has been used extensively in China, Russia and Japan as an adaptogen to fight against stress and fatigue. Aim of the study: The present study was designed to ascertain the anti-fatigue property of Acanthopanax senticosus by load-weighted swimming test, sleep deprivation test, also to isolate and characterize the active constituents. Materials and methods: Animals were orally administered with the extract of Acanthopanax senticosus. The anti-fatigue effects of the four fractions with different polarities from the 80% ethanol extract, and the different eluates collected from D101 macroporous resin chromatography and eleutheroside E, were examined based on the weight-loaded swimming capacity (physical fatigue) and the change of biochemical parameters in ICR mice. Moreover, the active fraction was later submitted to sleep-deprived mice (mental fatigue). Results: The results shown that the n-butanol fraction significant extends the swimming time of mice to exhaustion. Furthermore, the 60% ethanol–water eluate, more purified eleutherosides (including eleutheroside E, E2 and derivatives), were the exactly active constituents. Two compounds were isolated, which were identified as eleutheroside E, E2. Conclusions: The eleutherosides possess the potent abilities to alleviate fatigue both in physical and mental fatigue. Eleutheroside E may be responsible for the pharmacological effect of anti-fatigue. Furthermore, the possible mechanisms were reduced the level of TG by increasing fat utilization, delayed the accumulation of blood urea nitrogen (BUN), and increased the LDH to reduce the accumulation of lactic acid in muscle and then protect the muscle tissue. [Copyright &y& Elsevier]