Towards Unsupervised Speech Recognition And Synthesis With Quantized Speech Representation Learning

This video program is a part of the Premium package:

Towards Unsupervised Speech Recognition And Synthesis With Quantized Speech Representation Learning


  • IEEE MemberUS $11.00
  • Society MemberUS $0.00
  • IEEE Student MemberUS $11.00
  • Non-IEEE MemberUS $15.00
Purchase

Towards Unsupervised Speech Recognition And Synthesis With Quantized Speech Representation Learning

0 views
  • Share
In this paper we propose a Sequential Representation Quantization AutoEncoder (SeqRQ-AE) to learn from primarily unpaired audio data and produce sequences of representations very close to phoneme sequences of speech utterances. This is achieved by proper
In this paper we propose a Sequential Representation Quantization AutoEncoder (SeqRQ-AE) to learn from primarily unpaired audio data and produce sequences of representations very close to phoneme sequences of speech utterances. This is achieved by proper