Sound Signal Invariant DAE Neural Network-Based Quantizer Architecture of Audio/Speech Coder Using the Matching Pursuit AlgorithmAvramov, V. V.,
Herasimovich, V.,
Petrovsky, A. A.,
Аврамов, В. В.,
Герасимович, В. Ю.,
Петровский, А. А. of the input coded vector. Deep
autoencoder (DAE) neural network-based architecture for the quantization part
Раздельное моделирование речевого сообщения в виде Голосовых, фонетических и просодических параметров. The model uses an artificial neural network organized as
autoencoder that establishes correspondence between
Multi-Agent Systems for Collaborative Inference Based on Deep Policy Q-Inference Network suggests using an
autoencoder-based technique to reduce the size of intermediary features and constructing
Intelligent Resource Allocation Using an Artificial Ecosystem Optimizer with Deep Learning on UAV Networks scheduling, and trajectory design. To optimally allocate the UAV policies, the stacked sparse
autoencoder