Mengyuan Zhao 2015-12-28

From cslt Wiki
Jump to: navigation, search

RNN AM

  • AM training on big dataset --mengyuan
  • Further test nnet3-ctc training on 4000h 8k & 10000h 16k dataset. Tune decoding configures (phone-lm-weight, acwt, blank-scale), but ctc is still about 5 percent worse than standard nnet3.