First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs

Abstract

We present a method to perform first-pass large vocabulary continuous speech recognition using only a neural network and language model. Deep neural network acoustic models are now commonplace in HMM-based speech recognition systems, but building such systems is a complex, domain-specific task. Recent work demonstrated the feasibility of discarding the HMM sequence modeling framework by directly predicting transcript text from audio. This paper extends this approach in two ways. First, we demonstrate that a straightforward recurrent neural network architecture can achieve a high level of accuracy. Second, we propose and evaluate a modified prefix-search decoding algorithm. This approach to decoding enables first-pass speech recognition with a language model, completely unaided by the cumbersome infrastructure of HMM-based systems. Experiments on the Wall Street Journal corpus demonstrate fairly competitive word error rates, and the importance of bi-directional network recurrence.

Cited by in corpus (33)

• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• cuDNN: Efficient Primitives for Deep Learning
• An Actor-Critic Algorithm for Sequence Prediction
• EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decoding
• Self-Attention Networks for Connectionist Temporal Classification in Speech Recognition
• Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview
• Exploring Neural Transducers for End-to-End Speech Recognition
• Character-Level Incremental Speech Recognition with Recurrent Neural Networks
• On Multiplicative Integration with Recurrent Neural Networks
• Letter-Based Speech Recognition with Gated ConvNets
• Task Loss Estimation for Sequence Prediction
• Low Latency End-to-End Streaming Speech Recognition with a Scout Network
• Radio2Text: Streaming Speech Recognition Using mmWave Radio Signals
• End-to-end named entity extraction from speech
• Bidirectional Recurrent Neural Networks as Generative Models - Reconstructing Gaps in Time Series
• On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition
• Emphasizing Unseen Words: New Vocabulary Acquisition for End-to-End Speech Recognition
• Attention-based Wav2Text with Feature Transfer Learning
• Improving End-to-End Speech Recognition with Policy Learning
• End-to-End Feedback Loss in Speech Chain Framework via Straight-Through Estimator
• One In A Hundred: Select The Best Predicted Sequence from Numerous Candidates for Streaming Speech Recognition
• A Comparison of Hybrid and End-to-End Models for Syllable Recognition
• End-to-end attention-based distant speech recognition with Highway LSTM
• Sequence-to-Sequence ASR Optimization via Reinforcement Learning
• Back from the future: bidirectional CTC decoding using future information in speech recognition
• KT-Speech-Crawler: Automatic Dataset Construction for Speech Recognition from YouTube Videos
• Multi-scale Alignment and Contextual History for Attention Mechanism in Sequence-to-sequence Model
• Cascaded CNN-resBiLSTM-CTC: An End-to-End Acoustic Model For Speech Recognition
• Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers
• Topic Model Robustness to Automatic Speech Recognition Errors in Podcast Transcripts
• Exploiting Nontrivial Connectivity for Automatic Speech Recognition
• An Investigation of Enhancing CTC Model for Triggered Attention-based Streaming ASR
• Phoneme Level Language Models for Sequence Based Low Resource ASR