QR kód

A Light-Weight Autoregressive CNN-Based Frame Level Transducer Decoder for End-to-End ASR

A convolutional neural network (CNN) transducer decoder was proposed to reduce the decoding time of an end-to-end automatic speech recognition (ASR) system while maintaining accuracy. The CNN of 177 k parameters and a kernel size of 6 generates the probabilities of the current token at the token lev...

Celý popis

Uloženo v:
Hlavní autoři: Hyeon-Kyu Noh, Hong-June Park
Médium: Artigo
Jazyk:Inglês
Vydáno: MDPI AG 2024-02-01
Edice:Applied Sciences
Témata:
speech recognition
autoregressive speech recognition
end-to-end
CNN
transducer decoder
On-line přístup:https://www.mdpi.com/2076-3417/14/3/1300
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Podobné jednotky