arXiv (Cornell University) · 2018 · 43 citations · 13 references
ComputingComputer ScienceNatural Language ProcessingPhoneticsPhonologyLanguage ModelingSpeech RecognitionAttention-based Speech RecognitionCode-switchingCode-switching Speech RecognitionEnd-to-end Speech RecognitionError Rate AnalysisError Rate Metrics
Code-switching speech recognition has attracted an increasing interest recently, but the need for expert linguistic knowledge has always been a big issue. End-to-end automatic speech recognition (ASR) simplifies the building of ASR systems considerably by predicting graphemes or characters directly from acoustic input. In the mean time, the need of expert linguistic knowledge is also eliminated, which makes it an attractive choice for code-switching ASR. This paper presents a hybrid CTC-Attention based end-to-end Mandarin-English code-switching (CS) speech recognition system and studies the effect of hybrid CTC-Attention based models, different modeling units, the inclusion of language identification and different decoding strategies on the task of code-switching ASR. On the SEAME corpus, our system achieves a mixed error rate (MER) of 34.24%.
13
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Martı́n Abadi, Ashish Agarwal, Paul Barham et al. · arXiv (Cornell University) · 2016 · 9.8K citations · Full text
Connectionist temporal classification
Alex Graves, Santiago Fernández, Faustino Gomez et al. · 2006 · 5.4K citations
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
Dario Amodei, Rishita Anubhai, Eric Battenberg et al. · arXiv (Cornell University) · 2015 · 2.2K citations · Full text