# Multi-Level Embedding Conformer Framework for Bengali Automatic Speech Recognition

arXiv: https://arxiv.org/abs/2601.09710 · HTML: https://mlsanity.com/paper/2601.09710/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 21 references that are in the map.
- First posted on arXiv 23 Dec 2025.

## Builds on (most cited first, 7 of 7)

- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation](https://mlsanity.com/paper/2011.00747/) (2020)
- [Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese](https://mlsanity.com/paper/1804.10752/) (2018)
- [End-to-End Multi-Channel Transformer for Speech Recognition](https://mlsanity.com/paper/2102.03951/) (2021)
- [An Automatic Speech Recognition System for Bengali Language based on Wav2Vec2 and Transfer Learning](https://mlsanity.com/paper/2209.08119/) (2022)
- [End-to-End Bengali Speech Recognition](https://mlsanity.com/paper/2009.09615/) (2020)

## Abstract (arXiv)

Bengali, spoken by over 300 million people, is a morphologically rich and lowresource language, posing challenges for automatic speech recognition (ASR). This research presents an end-to-end framework for Bengali ASR, building on a Conformer-CTC backbone with a multi-level embedding fusion mechanism that incorporates phoneme, syllable, and wordpiece representations. By enriching acoustic features with these linguistic embeddings, the model captures fine-grained phonetic cues and higher-level contextual patterns. The architecture employs early and late Conformer stages, with preprocessing steps including silence trimming, resampling, Log-Mel spectrogram extraction, and SpecAugment augmentation. The experimental results demonstrate the strong potential of the model, achieving a word error rate (WER) of 10.01% and a character error rate (CER) of 5.03%. These results demonstrate the effectiveness of combining multi-granular linguistic information with acoustic modeling, providing a scalable approach for low-resource ASR development.