{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T12:12:07Z","timestamp":1783339927702,"version":"3.54.6"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462682","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"1-5828","source":"Crossref","is-referenced-by-count":148,"title":["An Analysis of Incorporating an External Language Model into a Sequence-to-Sequence Model"],"prefix":"10.1109","author":[{"given":"Anjuli","family":"Kannan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonghui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"ZhiJeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rohit","family":"Prabhavalkar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","author":"hori","year":"2017","journal-title":"Advances in joint CTC-attention based end-to-end speech recognition with a deep CNN encoder and RNN-LM"},{"key":"ref11","article-title":"Cold fusion: Training seq2seq models together with language models","volume":"abs 1708 6426","author":"sriram","year":"2017","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref13","article-title":"Modeling coverage for neural machine translation","volume":"abs 1601 4811","author":"tu","year":"2016","journal-title":"CoRR"},{"key":"ref14","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","volume":"abs 1609 8144","author":"wu","year":"2016","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-343","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref17","first-page":"69","volume":"16","author":"mohri","year":"2002","journal-title":"Speech Recognition With Weighted Finite-State Transducers"},{"key":"ref18","first-page":"11","author":"allauzen","year":"2007","journal-title":"OpenFst A General and Efficient Weighted Finite-state Transducer Library"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-249","article-title":"Bayesian language model interpolation for mobile speech input","author":"allauzen","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref4","article-title":"Con-nectionist Temporal Classification: Labeling Unsegmented Seuqnece Data with Recurrent Neural Networks","author":"graves","year":"2006","journal-title":"Proc ICML"},{"key":"ref3","article-title":"Sequence transduction with recurrent neural networks","volume":"abs 1211 3711","author":"graves","year":"2012","journal-title":"CoRR"},{"key":"ref6","article-title":"Exploring the limits of language modeling","volume":"abs 1602 2410","author":"jozefowicz","year":"2016","journal-title":"CoRR"},{"key":"ref5","article-title":"A Comparison of Sequence-to-sequence Models for Speech Recognition","author":"prabhavalkar","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-343","article-title":"Towards Better Decoding and Language Model Integration in Sequence to Sequence Models","author":"chorowski","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref7","article-title":"On using monolingual corpora in neural machine translation","volume":"abs 1503 3535","author":"gulcehre","year":"2015","journal-title":"CoRR"},{"key":"ref2","article-title":"End-to-End Attention-based Large Vocabulary Speech Recognition","author":"bahdanau","year":"0","journal-title":"Proc ICASSP 2016"},{"key":"ref9","first-page":"137","volume":"35","author":"gulcehre","year":"2017","journal-title":"On integrating a language model into neural machine translation"},{"key":"ref1","article-title":"Listen, attend and spell","volume":"abs 1508 1211","author":"chan","year":"2015","journal-title":"CoRR"},{"key":"ref20","first-page":"799","article-title":"Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition","author":"schuster","year":"2005","journal-title":"Artificial Neural Networks Formal Models and Their Applications-ICANN"},{"key":"ref22","article-title":"Attention Is All You Need","volume":"abs 1706 3762","author":"vaswani","year":"2017","journal-title":"CoRR"},{"key":"ref21","author":"povey","year":"2011","journal-title":"Speech Recognition Toolkit"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-275"},{"key":"ref23","article-title":"Fast and Accurate Recurrent Neural Network Acoustic Models for Speech Recognition","author":"sak","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref26","article-title":"Exploring Architectures, Data and Units for Streaming End-to-End Speech Recognition with RNN-Transducer","author":"rao","year":"2017","journal-title":"Proc ASRU"},{"key":"ref25","author":"abadi","year":"2015","journal-title":"Tensorflow Large-scale machine learning on heterogeneous distributed systems"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB","start":{"date-parts":[[2018,4,15]]},"end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08462682.pdf?arnumber=8462682","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,2]],"date-time":"2022-09-02T10:47:07Z","timestamp":1662115627000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462682\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462682","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}