End-To-End Speech Recognition Using A High Rank LSTM-CTC Based Model

2019/03/12 by Shi, Yangyang, Hwang, Mei-Yuh, Lei, Xin
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1903.05261

Abstract

Long Short Term Memory Connectionist Temporal Classification (LSTM-CTC) based end-to-end models are widely used in speech recognition due to its simplicity in training and efficiency in decoding. In conventional LSTM-CTC based models, a bottleneck projection matrix maps the hidden feature vectors obtained from LSTM to softmax output layer. In this paper, we propose to use a high rank projection layer to replace the projection matrix. The output from the high rank projection layer is a weighted combination of vectors that are projected from the hidden feature vectors via different projection matrices and non-linear activation function. The high rank projection layer is able to improve the expressiveness of LSTM-CTC models. The experimental results show that on Wall Street Journal (WSJ) corpus and LibriSpeech data set, the proposed method achieves 4%-6% relative word error rate (WER) reduction over the baseline CTC system. They outperform other published CTC based end-to-end (E2E) models under the condition that no external data or data augmentation is applied. Code has been made available at https://github.com/mobvoi/lstm_ctc.

Related

• Improving LSTM-CTC based ASR performance in domains with limited training data
• High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model
• Improving CTC-based speech recognition via knowledge transferring from pre-trained language models
• Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large\n Vocabulary Speech Recognition
• An improved hybrid CTC-Attention model for speech recognition