Login / Signup

Language Identification Based on Generative Modeling of Posteriorgram Sequences Extracted from Frame-by-Frame DNNs and LSTM-RNNs.

Ryo MasumuraTaichi AsamiHirokazu MasatakiYushi AonoSumitaka Sakauchi
Published in: INTERSPEECH (2016)
Keyphrases
  • language identification
  • recurrent neural networks
  • video frames
  • echo state networks
  • multi modal
  • long short term memory