Shankar Kumar, M. Nirschl, D. Holtmann-Rice, H. Liao, A. Suresh, Felix X. Yu
{"title":"Lattice rescoring strategies for long short term memory language models in speech recognition","authors":"Shankar Kumar, M. Nirschl, D. Holtmann-Rice, H. Liao, A. Suresh, Felix X. Yu","doi":"10.1109/ASRU.2017.8268931","DOIUrl":null,"url":null,"abstract":"Recurrent neural network (RNN) language models (LMs) and Long Short Term Memory (LSTM) LMs, a variant of RNN LMs, have been shown to outperform traditional N-gram LMs on speech recognition tasks. However, these models are computationally more expensive than N-gram LMs for decoding, and thus, challenging to integrate into speech recognizers. Recent research has proposed the use of lattice-rescoring algorithms using RNNLMs and LSTMLMs as an efficient strategy to integrate these models into a speech recognition system. In this paper, we evaluate existing lattice rescoring algorithms along with new variants on a YouTube speech recognition task. Lattice rescoring using LSTMLMs reduces the word error rate (WER) for this task by 8% relative to the WER obtained using an N-gram LM.","PeriodicalId":290868,"journal":{"name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"36","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ASRU.2017.8268931","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 36
Abstract
Recurrent neural network (RNN) language models (LMs) and Long Short Term Memory (LSTM) LMs, a variant of RNN LMs, have been shown to outperform traditional N-gram LMs on speech recognition tasks. However, these models are computationally more expensive than N-gram LMs for decoding, and thus, challenging to integrate into speech recognizers. Recent research has proposed the use of lattice-rescoring algorithms using RNNLMs and LSTMLMs as an efficient strategy to integrate these models into a speech recognition system. In this paper, we evaluate existing lattice rescoring algorithms along with new variants on a YouTube speech recognition task. Lattice rescoring using LSTMLMs reduces the word error rate (WER) for this task by 8% relative to the WER obtained using an N-gram LM.