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

arXiv: https://arxiv.org/abs/1903.05261 · HTML: https://mlsanity.com/paper/1903.05261/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Mar 2019.

## Built on by (most cited first, 2 of 2)

- [Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency](https://mlsanity.com/paper/2104.02176/) (2021)
- [End-to-end LSTM based estimation of volcano event epicenter localization](https://mlsanity.com/paper/2110.14594/) (2021)

## Abstract (arXiv)

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.