Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition

Abstract

We present results that show it is possible to build a competitive, greatly simplified, large vocabulary continuous speech recognition system with whole words as acoustic units. We model the output vocabulary of about 100,000 words directly using deep bi-directional LSTM RNNs with CTC loss. The model is trained on 125,000 hours of semi-supervised acoustic training data, which enables us to alleviate the data sparsity problem for word models. We show that the CTC word models work very well as an end-to-end all-neural speech recognition model without the use of traditional context-dependent sub-word phone units that require a pronunciation lexicon, and without any language model removing the need to decode. We demonstrate that the CTC word models perform better than a strong, more complex, state-of-the-art baseline with sub-word units.

References in corpus (1)

• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin

Cited by in corpus (29)

• Mixed Precision Training
• End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures
• Long-term Forecasting using Higher Order Tensor RNNs
• Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence Labelling
• Tied & Reduced RNN-T Decoder
• Direct Acoustics-to-Word Models for English Conversational Speech Recognition
• Minimum Bayes Risk Training of RNN-Transducer for End-to-End Speech Recognition
• Multitask Learning with CTC and Segmental CRF for Speech Recognition
• Advancing Acoustic-to-Word CTC Model
• Improved training for online end-to-end speech recognition systems
• End-to-end Speech Recognition with Word-based RNN Language Models
• Deep context: end-to-end contextual speech recognition
• Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models
• Advancing Connectionist Temporal Classification With Attention Modeling
• Hybrid CTC-Attention based End-to-End Speech Recognition using Subword Units
• Phonemic and Graphemic Multilingual CTC Based Speech Recognition
• Sequence Prediction with Neural Segmental Models
• Recent Progresses in Deep Learning based Acoustic Models (Updated)
• High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model
• Linguistic Search Optimization for Deep Learning Based LVCSR
• Multi-Head Decoder for End-to-End Speech Recognition
• End-to-end contextual speech recognition using class language models and a token passing decoder
• Speech recognition for air traffic control via feature learning and end-to-end training
• Phonocardiographic Sensing using Deep Learning for Abnormal Heartbeat Detection
• Multilingual Adaptation of RNN Based ASR Systems
• Acoustic-to-Word Models with Conversational Context Information
• Speaker Adaptation for End-to-End CTC Models
• Linked Recurrent Neural Networks
• LSTM Acoustic Models Learn to Align and Pronounce with Graphemes