Papers › Neural Network Language Modeling with Letter-based Features and Importance Sampling

Neural Network Language Modeling with Letter-based Features and Importance Sampling

15 Apr 2018ICASSP 2018 4archive 2025-07-28

Hainan Xu, Ke Li, Yiming Wang, Jian Wang, Shiyin Kang, Xie Chen, Daniel Povey, Sanjeev Khudanpur

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 n-grams) 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.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModelingLanguage ModellingSpeech Recognitionspeech-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Recognition LibriSpeech test-clean tdnn + chain + rnnlm rescoring Word Error Rate (WER) 3.06 #47 of 64 Archive leaderboard report
Speech Recognition LibriSpeech test-other tdnn + chain + rnnlm rescoring Word Error Rate (WER) 7.63 #42 of 53 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SPEED

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections