Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM
We present a state-of-the-art end-to-end Automatic Speech Recognition (ASR) model. We learn to listen and write characters with a joint Connectionist Temporal Classification (CTC) and attention-based encoder-decoder network. The encoder is a deep Convolutional Neural Network (CNN) based on the VGG network. The CTC network sits on top of the encoder and is jointly trained with the attention-based decoder. During the beam search process, we combine the CTC predictions, the attention-based decoder predictions and a separately trained LSTM language model. We achieve a 5-10\% error reduction compared to prior systems on spontaneous Japanese and Chinese speech, and our end-to-end model beats out traditional hybrid ASR systems.
Code (6)
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderGeneral ClassificationLanguage ModelingLanguage ModellingSpeech RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Audio Adversarial Examples for Robust Hybrid CTC/Attention Speech Recognition
Recent advances in Automatic Speech Recognition (ASR) demonstrated how end-to-end systems are able to achieve state-of-the-art performance. There is a trend towards deeper neural networks, however those ASR models are al…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Decoderspeech-recognition+1Stream attention-based multi-array end-to-end speech recognition
Automatic Speech Recognition (ASR) using multiple microphone arrays has achieved great success in the far-field robustness. Taking advantage of all the information that each array shares and contributes is crucial in thi…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Decoderspeech-recognition+1Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling
Attention-based encoder-decoder neural network models have recently shown promising results in machine translation and speech recognition. In this work, we propose an attention-based neural network model for joint intent…
Decoderintent-classificationIntent ClassificationIntent Detection+2Multi-encoder multi-resolution framework for end-to-end speech recognition
Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end Automatic Speech Recognition (ASR). The joint CTC/Attention model has achieved great …
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionMultichannel End-to-end Speech Recognition
The field of speech recognition is in the midst of a paradigm shift: end-to-end neural networks are challenging the dominance of hidden Markov models as a core technology. Using an attention mechanism in a recurrent enco…
DecoderLanguage ModelingLanguage ModellingSpeech Enhancement+2