# A Novel Learnable Dictionary Encoding Layer for End-to-End Language Identification

arXiv: https://arxiv.org/abs/1804.00385 · HTML: https://mlsanity.com/paper/1804.00385/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Apr 2018.

## Built on by (most cited first, 7 of 7)

- [Mixture-of-Shape-Experts (MoSE): End-to-End Shape Dictionary Framework to Prompt SAM for Generalizable Medical Segmentation](https://mlsanity.com/paper/2504.09601/) (2025)
- [Class Token and Knowledge Distillation for Multi-head Self-Attention Speaker Verification Systems](https://mlsanity.com/paper/2111.03842/) (2021)
- [Neural Inference of Gaussian Processes for Time Series Data of Quasars](https://mlsanity.com/paper/2211.10305/) (2022)
- [Distilling Multi-Level X-vector Knowledge for Small-footprint Speaker Verification](https://mlsanity.com/paper/2303.01125/) (2023)
- [Towards Attention-based Contrastive Learning for Audio Spoof Detection](https://mlsanity.com/paper/2407.03514/) (2024)
- [On Barriers to Archival Audio Processing](https://mlsanity.com/paper/2507.08768/) (2025)
- [Spectrogram features for audio and speech analysis](https://mlsanity.com/paper/2603.14917/) (2026)

## Abstract (arXiv)

A novel learnable dictionary encoding layer is proposed in this paper for end-to-end language identification. It is inline with the conventional GMM i-vector approach both theoretically and practically. We imitate the mechanism of traditional GMM training and Supervector encoding procedure on the top of CNN. The proposed layer can accumulate high-order statistics from variable-length input sequence and generate an utterance level fixed-dimensional vector representation. Unlike the conventional methods, our new approach provides an end-to-end learning framework, where the inherent dictionary are learned directly from the loss function. The dictionaries and the encoding representation for the classifier are learned jointly. The representation is orderless and therefore appropriate for language identification. We conducted a preliminary experiment on NIST LRE07 closed-set task, and the results reveal that our proposed dictionary encoding layer achieves significant error reduction comparing with the simple average pooling.