# Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition

arXiv: https://arxiv.org/abs/1806.07789 · HTML: https://mlsanity.com/paper/1806.07789/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2018.

## Built on by (most cited first, 21 of 21)

- [Compacter: Efficient Low-Rank Hypercomplex Adapter Layers](https://mlsanity.com/paper/2106.04647/) (2021)
- [Clifford Neural Layers for PDE Modeling](https://mlsanity.com/paper/2209.04934/) (2022)
- [Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with 1/n Parameters](https://mlsanity.com/paper/2102.08597/) (2021)
- [A Survey of Sound Source Localization with Deep Learning Methods](https://mlsanity.com/paper/2109.03465/) (2021)
- [Convolutional Hypercomplex Embeddings for Link Prediction](https://mlsanity.com/paper/2106.15230/) (2021)
- [Speech Emotion Recognition Using Quaternion Convolutional Neural Networks](https://mlsanity.com/paper/2111.00404/) (2021)
- [QuatDE: Dynamic Quaternion Embedding for Knowledge Graph Completion](https://mlsanity.com/paper/2105.09002/) (2021)
- [Learning Speech Emotion Representations in the Quaternion Domain](https://mlsanity.com/paper/2204.02385/) (2022)
- [Q-RBSA: High-Resolution 3D EBSD Map Generation Using An Efficient Quaternion Transformer Network](https://mlsanity.com/paper/2303.10722/) (2023)
- [Two-view Graph Neural Networks for Knowledge Graph Completion](https://mlsanity.com/paper/2112.09231/) (2021)
- [Quaternion Convolutional Neural Networks: Current Advances and Future Directions](https://mlsanity.com/paper/2307.08663/) (2023)
- [Learning Characteristics of Reverse Quaternion Neural Network](https://mlsanity.com/paper/2411.05816/) (2024)
- [Quaternion-Valued Convolutional Neural Network Applied for Acute Lymphoblastic Leukemia Diagnosis](https://mlsanity.com/paper/2112.06685/) (2021)
- [Enhancing ResNet Image Classification Performance by using Parameterized Hypercomplex Multiplication](https://mlsanity.com/paper/2301.04623/) (2023)
- [Fully tensorial approach to hypercomplex-valued neural networks](https://mlsanity.com/paper/2407.00449/) (2024)
- [Quaternion Self-Attention with Shared Scores](https://mlsanity.com/paper/2605.24920/) (2026)
- [Quaternion-Based Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2111.10536/) (2021)
- [QuatE-D: A Distance-Based Quaternion Model for Knowledge Graph Embedding](https://mlsanity.com/paper/2504.13983/) (2025)
- [Compressing Quaternion Convolutional Neural Networks for Audio Classification](https://mlsanity.com/paper/2510.21388/) (2025)
- [QC-GAN: A Parameter-Efficient Quaternion Conformer GAN for High-Fidelity Speech Enhancement](https://mlsanity.com/paper/2606.18611/) (2026)
- [QSV: Quat-Sphere-Vision for Coupled Quaternion Attention on Spherical Lattices](https://mlsanity.com/paper/2609.30592/) (2026)

## Abstract (arXiv)

Recently, the connectionist temporal classification (CTC) model coupled with recurrent (RNN) or convolutional neural networks (CNN), made it easier to train speech recognition systems in an end-to-end fashion. However in real-valued models, time frame components such as mel-filter-bank energies and the cepstral coefficients obtained from them, together with their first and second order derivatives, are processed as individual elements, while a natural alternative is to process such components as composed entities. We propose to group such elements in the form of quaternions and to process these quaternions using the established quaternion algebra. Quaternion numbers and quaternion neural networks have shown their efficiency to process multidimensional inputs as entities, to encode internal dependencies, and to solve many tasks with less learning parameters than real-valued models. This paper proposes to integrate multiple feature views in quaternion-valued convolutional neural network (QCNN), to be used for sequence-to-sequence mapping with the CTC model. Promising results are reported using simple QCNNs in phoneme recognition experiments with the TIMIT corpus. More precisely, QCNNs obtain a lower phoneme error rate (PER) with less learning parameters than a competing model based on real-valued CNNs.