EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Language Recognition Method of Convolutional Neural Network Based on Spectrogram

Wu Min, Zhu Shanshan

Journal of Education, Teaching and Social Studies · 2019

DOI: 10.22158/jetss.v1n2p113 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Education, Teaching and Social Studies, 2019. Verfasst von Wu Min und 1 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Language recognition is an important branch of speech technology. As a front-end technology of speech information processing, higher recognition accuracy is required. It is found through research that there are obvious differences between the language maps of different languages, which can be used for language identification. This paper uses a convolutional neural network as a classification model, and compares the language recognition effects of traditional language recognition features and spectrogram features on the five language recognition tasks of Chinese, Japanese, Vietnamese, Russian, and Spanish through experiments. The best effect is the ivector feature, and the spectrogram feature has a higher F value than the low-dimensional ivector feature.

Zitieren

APA

Min, W., & Shanshan, Z. (2019). Language Recognition Method of Convolutional Neural Network Based on Spectrogram. Journal of Education, Teaching and Social Studies. https://doi.org/10.22158/jetss.v1n2p113

Vancouver

Min W, Shanshan Z. Language Recognition Method of Convolutional Neural Network Based on Spectrogram. Journal of Education, Teaching and Social Studies. 2019. doi:10.22158/jetss.v1n2p113

BibTeX
@article{Min2019,
  author = {Min, Wu and Shanshan, Zhu},
  title = {Language Recognition Method of Convolutional Neural Network Based on Spectrogram},
  journal = {Journal of Education, Teaching and Social Studies},
  year = {2019},
  doi = {10.22158/jetss.v1n2p113}
}
Kostenlos starten →