A hybrid model for pathological voice recognition of post-stroke dysarthria by using 1DCNN and double-LSTM networks

Ye, Wujian; Jiang, Zixing; Li, Qi; Liu, Yijun; Mou, Zhiwei

doi:10.1016/j.apacoust.2022.108934

Cited by 16 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Speech synthesis technology refers to the technology that converts text information into speech data and then plays it out in the form of speech [30]. Speech synthesis technology can be divided into three modules: text analysis, prosodic modeling and speech synthesis.…”

Section: Multimedia Human-computer Interaction Technologymentioning

confidence: 99%

Application of Multimedia Human-Computer Interaction Technology in Preschool Children Drama Education

Gong

2022

Advances in Multimedia

View full text Add to dashboard Cite

With the continuous development of multimedia technology and children’s drama education as a very important part of preschool education, the combination of the two has attracted the attention of many scholars at home and abroad. Drama education for preschool children is the initial stage of children’s learning and the most important part of preschool education system. At the same time, preschool children drama education is the most basic stage of children’s intellectual development. The correct and reasonable preschool children drama education plays a great role in promoting their intelligence and development. The drama education for preschool children based on multimedia human-computer interaction technology not only expands new teaching methods for the traditional drama education model but also provides a good platform for teachers to choose teaching resources and injects new vitality into preschool children’s music education. This paper proposes the application of multimedia human-computer interaction technology in preschool children’s drama education. We analyze the current preschool children’s drama education curriculum reform that has limitations. The level of teachers’ drama education needs to be improved. Young children lack awareness of drama. Drama education for children lacks strong support from parents and other problems. In order to solve the above problems, we focus on voice interaction technology, image interaction technology, and somatosensory interaction technology in multimedia human-computer interaction technology, which establishes a set of teacher-multimedia-student three-dimensional crossover multidirection learning activity modes. In the multidirection learning mode, students can quickly develop their sense of rhythm. Teachers use image interaction technology to guide students to think about the relationship between content and form, so as to gradually form their own unique style of drama. At the same time, somatosensory interaction technology can cultivate teaching tasks seamlessly connected with the environment, so that students can follow the hologram through hands-on practice. Finally, this paper sets up a questionnaire on the experience of human-computer interaction mode in preschool children’s drama education, mainly to conduct a questionnaire survey on front-line drama teachers, aiming at preschool children’s drama learning activities and teachers’ teaching methods. In numerical experiments, we show teachers’ evaluation of the teaching effect of speech synthesis technology integrated into preschool children’s drama education and the classroom effect evaluation of speech synthesis technology integrated into preschool children’s drama education. The evaluation results show that the application effect of multimedia human-computer interaction technology in preschool children’s drama education is good, which can provide better services for preschool children’s drama education.

show abstract

Section: Multimedia Human-computer Interaction Technologymentioning

confidence: 99%

Application of Multimedia Human-Computer Interaction Technology in Preschool Children Drama Education

Gong

2022

Advances in Multimedia

View full text Add to dashboard Cite

show abstract

“…To further verify the superiority of the selected method and the fairness of the experiment, this article selects the traditional 1DCNN 36 and SVR 37,38 models as comparative experiments. Aer 60 repeated experiments under different pretreatments and dimensionality reduction, the average output performance indicators of the test set are shown in Table 2.…”

Section: Analytical Methods Papermentioning

confidence: 99%

Research on transformer fault diagnosis based on an IWHO optimized MS1DCNN algorithm and LIF spectrum

Yan¹,

Chen²,

Kan³

et al. 2023

Anal. Methods

View full text Add to dashboard Cite

show abstract

“…However, in deeper neural network structures, the BP algorithm is prone to encounter the problem of gradient disappearance or gradient explosion, leading to difficulties in network training. In recent years, long short-term memory network models (LSTM) have gradually gained attention [13][14]. By introducing memory units and gating mechanisms, LSTM can effectively capture and maintain long-term time-dependent relationships, and has better modeling ability for long sequence data.…”

Section: Introductionmentioning

confidence: 99%

Reflection signal classification of deep-sea surface sediment based on 1DCNN-DLSTM networks

Qu,

Zhi,

Cao

et al. 2023

International Workshop on Signal Processing and Machine Learning (WSPML 2023)

View full text Add to dashboard Cite

A hybrid model for pathological voice recognition of post-stroke dysarthria by using 1DCNN and double-LSTM networks

Cited by 16 publications

References 18 publications

Application of Multimedia Human-Computer Interaction Technology in Preschool Children Drama Education

Application of Multimedia Human-Computer Interaction Technology in Preschool Children Drama Education

Research on transformer fault diagnosis based on an IWHO optimized MS1DCNN algorithm and LIF spectrum

Reflection signal classification of deep-sea surface sediment based on 1DCNN-DLSTM networks

Contact Info

Product

Resources

About