# Bidirectional Quaternion Long-Short Term Memory Recurrent Neural Networks for Speech Recognition

arXiv: https://arxiv.org/abs/1811.02566 · HTML: https://mlsanity.com/paper/1811.02566/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Nov 2018.

## Built on by (most cited first, 1 of 1)

- [KHNNs: hypercomplex neural networks computations via Keras using TensorFlow and PyTorch](https://mlsanity.com/paper/2407.00452/) (2024)

## Abstract (arXiv)

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 speech recognition tasks, due to their efficient representation of long and short term dependencies in sequences of inter-dependent features. Nonetheless, internal dependencies within the element composing multidimensional features are weakly considered by traditional real-valued representations. We propose a novel quaternion long-short term memory (QLSTM) recurrent neural network that takes into account both the external relations between the features composing a sequence, and these internal latent structural dependencies with the quaternion algebra. QLSTMs are compared to LSTMs during a memory copy-task and a realistic application of speech recognition on the Wall Street Journal (WSJ) dataset. QLSTM reaches better performances during the two experiments with up to 2.8 times less learning parameters, leading to a more expressive representation of the information.