Designing of Gabor filters for spectro-temporal feature extraction to improve the performance of ASR system

Dutta, Anirban; Ashishkumar, Gudmalwar; Rao, Ch. V. Rama

doi:10.1007/s10772-019-09650-5

Cited by 5 publications

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To this end, the article proposes a cascading method, which is improved on the basis of hybrid HMM/ANN (Dutta, et al 2019), combining the feature distinguishing processing ability of ANN and the representation ability of the mixed Gaussian model for complex distributions. The feature sequence of speech is used as the input of ANN, and the classification output result of ANN is regularized as the training feature of the traditional Gaussian mixture model.…”

Section: Influencing Factors Of Speech Recognition Technology In Engl...mentioning

confidence: 99%

Influencing Neutrosophic Factors of Speech Recognition Technology in English Collection

Chu

Liu

2022

Journal of Cases on Information Technology

View full text Add to dashboard Cite

Based on the research and analysis of speech recognition system and neural network principle, combined with English related decision tree, this paper completes the construction and design of English speech recognition based on hybrid frame and series frame neural system network. Combined with relevant information, this paper analyzes the influencing factors of language recognition technology in English collection under neural network. This paper proposes a method of English Corpus collection. Through the speech recognition technology under the neural network, experiments are carried out by using the neural network algorithm, K-means clustering algorithm and HMM / Ann cascade system to analyze the influencing factors of speech recognition technology based on the neural network in English collection. Finally, from the English accent, the amount of speech information make a detailed analysis of the proportion of speech fuzziness, speech speed and environmental interference, so as to draw a conclusion.

show abstract

Section: Influencing Factors Of Speech Recognition Technology In Engl...mentioning

confidence: 99%