极度视界

Courses:1.EECS E6870 — Fall 2012 Speech Recognition2.CSE 6328 SPEECH AND LANGUAGE PROCESSING (FALL 2012)开源工具(C/C++)：1. HTK (较久远，早已不更新，)2.kaldi (11年开始，很棒的学习工具，支持CUDA；有DNN+HMM)larg

通过src/util/parse-options.h 中定义的ParseOptions类来解析参数Shell脚本的使用：src/nnetbin/nnet-train-frmshuff.cc 用来训练神经网络 即上图 train_tool=nnet-train-frmshuff NnetTrainOptions trn_opts; trn_o

训练神经网络片段：{ # Train the MLPtrain_ali=exp/tri4b_train_alicv_ali=exp/tri4b_dev_ali$cuda_cmd $dir/log/train_nnet.log \ steps/train_nnet.sh --copy-feats false \ --apply-cmvn true --norm-vars tru

IBM系：【1】B. Kingsbury, “Lattice-Based Optimization of Sequence Classification Criteria for Neural-Network Acoustic Modeling,” in Proc. ICASSP,2009.【2】Kingsbury B, Sainath T N, Soltau H. Scalable Mi

1.IEEE Transactions on Audio, Speech and Language Processing 2.Computer Speech and Language3.ICASSP 4.Interspeech 5.IEEE workshops on ASRU6.WiSSAP