Towards End-To-End Speech Recognition with Recurrent Neural Networks
This paper presents a speech recognition system that directly transcribes audio data with text, without requiring an intermediate phonetic representation. The system is based on a combination of the deep bidirectional LSTM recurrent neural network architecture and the Connectionist Temporal Classification objective function. A modification to the objective function is introduced that trains the network to minimise the expectation of an arbitrary transcription loss function. This allows a direct optimisation of the word error rate, even in the absence of a lexicon or language model. The system achieves a word error rate of 27.3% on the Wall Street Journal corpus with no prior linguistic information, 21.9% with only a lexicon of allowed words, and 8.2% with a trigram language model. Combining the network with a baseline system further reduces the error rate to 6.7%.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage Modellingspeech-recognitionSpeech RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Multi-task Recurrent Model for Speech and Speaker Recognition
Although highly correlated, speech and speaker recognition have been regarded as two independent tasks and studied by two communities. This is certainly not the way that people behave: we decipher both speech content and…
Speaker RecognitionBidirectional Quaternion Long-Short Term Memory Recurrent Neural Networks for Speech Recognition
Recurrent neural networks (RNN) are at the core of modern automatic speech recognition (ASR) systems. In particular, long-short term memory (LSTM) recurrent neural networks have achieved state-of-the-art results in many …
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionMulti-task Recurrent Model for True Multilingual Speech Recognition
Research on multilingual speech recognition remains attractive yet challenging. Recent studies focus on learning shared structures under the multi-task paradigm, in particular a feature sharing structure. This approach h…
speech-recognitionSpeech RecognitionEncoding Word Confusion Networks with Recurrent Neural Networks for Dialog State Tracking
This paper presents our novel method to encode word confusion networks, which can represent a rich hypothesis space of automatic speech recognition systems, via recurrent neural networks. We demonstrate the utility of ou…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)dialog state trackingspeech-recognition+1Automatic speech recognition for launch control center communication using recurrent neural networks with data augmentation and custom language model
Transcribing voice communications in NASA's launch control center is important for information utilization. However, automatic speech recognition in this environment is particularly challenging due to the lack of trainin…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data AugmentationLanguage Modeling+3