Eric Battenberg, Jitong Chen, Rewon Child, Adam Coates, Yashesh Gaur Yi Li, Hairong Liu, S. Satheesh, Anuroop Sriram, Zhenyao Zhu
{"title":"探索端到端语音识别的神经传感器","authors":"Eric Battenberg, Jitong Chen, Rewon Child, Adam Coates, Yashesh Gaur Yi Li, Hairong Liu, S. Satheesh, Anuroop Sriram, Zhenyao Zhu","doi":"10.1109/ASRU.2017.8268937","DOIUrl":null,"url":null,"abstract":"In this work, we perform an empirical comparison among the CTC, RNN-Transducer, and attention-based Seq2Seq models for end-to-end speech recognition. We show that, without any language model, Seq2Seq and RNN-Transducer models both outperform the best reported CTC models with a language model, on the popular Hub5'00 benchmark. On our internal diverse dataset, these trends continue — RNN-Transducer models rescored with a language model after beam search outperform our best CTC models. These results simplify the speech recognition pipeline so that decoding can now be expressed purely as neural network operations. We also study how the choice of encoder architecture affects the performance of the three models — when all encoder layers are forward only, and when encoders downsample the input representation aggressively.","PeriodicalId":290868,"journal":{"name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"217","resultStr":"{\"title\":\"Exploring neural transducers for end-to-end speech recognition\",\"authors\":\"Eric Battenberg, Jitong Chen, Rewon Child, Adam Coates, Yashesh Gaur Yi Li, Hairong Liu, S. Satheesh, Anuroop Sriram, Zhenyao Zhu\",\"doi\":\"10.1109/ASRU.2017.8268937\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this work, we perform an empirical comparison among the CTC, RNN-Transducer, and attention-based Seq2Seq models for end-to-end speech recognition. We show that, without any language model, Seq2Seq and RNN-Transducer models both outperform the best reported CTC models with a language model, on the popular Hub5'00 benchmark. On our internal diverse dataset, these trends continue — RNN-Transducer models rescored with a language model after beam search outperform our best CTC models. These results simplify the speech recognition pipeline so that decoding can now be expressed purely as neural network operations. We also study how the choice of encoder architecture affects the performance of the three models — when all encoder layers are forward only, and when encoders downsample the input representation aggressively.\",\"PeriodicalId\":290868,\"journal\":{\"name\":\"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)\",\"volume\":\"24 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-07-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"217\",\"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.2017.8268937\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ASRU.2017.8268937","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Exploring neural transducers for end-to-end speech recognition
In this work, we perform an empirical comparison among the CTC, RNN-Transducer, and attention-based Seq2Seq models for end-to-end speech recognition. We show that, without any language model, Seq2Seq and RNN-Transducer models both outperform the best reported CTC models with a language model, on the popular Hub5'00 benchmark. On our internal diverse dataset, these trends continue — RNN-Transducer models rescored with a language model after beam search outperform our best CTC models. These results simplify the speech recognition pipeline so that decoding can now be expressed purely as neural network operations. We also study how the choice of encoder architecture affects the performance of the three models — when all encoder layers are forward only, and when encoders downsample the input representation aggressively.