Sorry, you need to enable JavaScript to visit this website.

NEURAL NETWORK LANGUAGE MODELING WITH LETTER-BASED FEATURES AND IMPORTANCE SAMPLING

Citation Author(s):
Hainan Xu, Ke Li, Yiming Wang, Jian Wang, Shiyin Kang, Xie Chen, Daniel Povey, Sanjeev Khudanpur
Submitted by:
Hainan Xu
Last updated:
19 April 2018 - 11:52pm
Document Type:
Poster
Document Year:
2018
Event:
Presenters:
Hainan Xu
Paper Code:
3403
 

In this paper we describe an extension of the Kaldi software toolkit to support neural-based language modeling, intended for use in automatic speech recognition (ASR) and related tasks. We combine the use of subword features (letter ngrams) and one-hot encoding of frequent words so that the models can handle large vocabularies containing infrequent words. We propose a new objective function that allows for training of unnormalized probabilities. An importance sampling based method is supported to speed up training when the vocabulary is large. Experimental results on five corpora show that Kaldi-RNNLM rivals other recurrent neural network language model toolkits both on performance and training speed.

up
0 users have voted: