Diversity-Controllable and Accurate Audio Captioning Based on Neural Condition.

Xuenan Xu Mengyue Wu Kai Yu

Published in: ICASSP (2022)

Keyphrases

neural network
multimedia
signal processing
network architecture
computationally efficient
bio inspired
information retrieval
learning algorithm
e learning
high level
high accuracy
sufficient conditions
high precision
audio visual
speaker identification
audio signals