# An Empirical Study on the Impact of Positional Encoding in Transformer-based Monaural Speech Enhancement

arXiv: https://arxiv.org/abs/2401.09686 · HTML: https://mlsanity.com/paper/2401.09686/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jan 2024.

## Built on by (most cited first, 5 of 5)

- [Mamba in Speech: Towards an Alternative to Self-Attention](https://mlsanity.com/paper/2405.12609/) (2024)
- [AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancement](https://mlsanity.com/paper/2501.15417/) (2025)
- [SAV-SE: Scene-aware Audio-Visual Speech Enhancement with Selective State Space Model](https://mlsanity.com/paper/2411.07751/) (2024)
- [Selective State Space Model for Monaural Speech Enhancement](https://mlsanity.com/paper/2411.06217/) (2024)
- [Attention-Enhanced Graph Filtering for False Data Injection Attack Detection and Localization](https://mlsanity.com/paper/2601.18981/) (2026)

## Abstract (arXiv)

Transformer architecture has enabled recent progress in speech enhancement. Since Transformers are position-agostic, positional encoding is the de facto standard component used to enable Transformers to distinguish the order of elements in a sequence. However, it remains unclear how positional encoding exactly impacts speech enhancement based on Transformer architectures. In this paper, we perform a comprehensive empirical study evaluating five positional encoding methods, i.e., Sinusoidal and learned absolute position embedding (APE), T5-RPE, KERPLE, as well as the Transformer without positional encoding (No-Pos), across both causal and noncausal configurations. We conduct extensive speech enhancement experiments, involving spectral mapping and masking methods. Our findings establish that positional encoding is not quite helpful for the models in a causal configuration, which indicates that causal attention may implicitly incorporate position information. In a noncausal configuration, the models significantly benefit from the use of positional encoding. In addition, we find that among the four position embeddings, relative position embeddings outperform APEs.