lattice-free MMI HMM+GMM是一套非常经(gu)典(lao)的语音识别模型, 用GMM这个生成模型作为声学模型去估计单帧的似然, 然后用HMM连接去估计整个输入序列的似然. 随着时代的进步,GMM被DNN取代, 用DNN来代替GMM可以提高声学模型的准确性,再后来就是各种深度模型: LSTM, CNN等等. HMM的假设太强了! 在实际中并不...
MMI训练解lattice放在GPU上做（实现时使用了一些trick，包括LM使用4-gram的phone LM等），不需要像传统...
Lattice free MMIAcoustic modelingChildren speech recognitionVocal tract length normalizationThe progress of Automatic Speech Recognition (ASR) for children has been slower in languages with limited resources due to various challenges such as lack of training data, differences in acoustics, and intrinsic ...
In this paper we describe a method to perform sequence-discriminative training of neural network acoustic models without the need for frame-level cross-entropy pre-training. We use the lattice-free version of the maximum mutual information (MMI) criterion: LF-MMI. To make its computation feasible...
Yanhua Long, Yijie Li, Hone Ye, and Hongwei Mao, "Domain adaptation of lattice-free mmi based tdnn models for speech recognition," International Journal of Speech Technology, vol. 20, no. 1, pp. 171-178, 2017.Y. Long, Y. Li, H. Ye, and H. Mao, "Domain adaptation of lattice-...
Lattice-free maximum mutual information (LFMMI) was recently proposed as a mixture of the ideas of hidden-Markov-model-based acoustic models (AMs) and connectionist-temporal-classification-based AMs. In this paper, we investigate LFMMI from various perspectives of model combination, teacher-student ...
We present novel methods to train a hybrid DNN/HMM wake word detection system from partially labeled training data, and to use it in on-line applications: (i) we remove the prerequisite of frame-level alignments in the LF-MMI training algorithm, permitting the use of un-transcribed training ...