# A review of on-device fully neural end-to-end automatic speech recognition algorithms

arXiv: https://arxiv.org/abs/2012.07974 · HTML: https://mlsanity.com/paper/2012.07974/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2020.

## Built on by (most cited first, 13 of 13)

- [Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet](https://mlsanity.com/paper/2110.08352/) (2021)
- [Benchmarking Ultra-Low-Power μNPUs](https://mlsanity.com/paper/2503.22567/) (2025)
- [Two-Pass End-to-End ASR Model Compression](https://mlsanity.com/paper/2201.02741/) (2022)
- [PENTATRON: PErsonalized coNText-Aware Transformer for Retrieval-based cOnversational uNderstanding](https://mlsanity.com/paper/2210.12308/) (2022)
- [HebDB: a Weakly Supervised Dataset for Hebrew Speech Processing](https://mlsanity.com/paper/2407.07566/) (2024)
- [Noisy Training Improves E2E ASR for the Edge](https://mlsanity.com/paper/2107.04677/) (2021)
- [Semi-supervised transfer learning for language expansion of end-to-end speech recognition models to low-resource languages](https://mlsanity.com/paper/2111.10047/) (2021)
- [StableEmit: Selection Probability Discount for Reducing Emission Latency of Streaming Monotonic Attention ASR](https://mlsanity.com/paper/2107.00635/) (2021)
- [On the compression of shallow non-causal ASR models using knowledge distillation and tied-and-reduced decoder for low-latency on-device speech recognition](https://mlsanity.com/paper/2312.09842/) (2023)
- [Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment](https://mlsanity.com/paper/2501.18157/) (2025)
- [Towards Personalization of CTC Speech Recognition Models with Contextual Adapters and Adaptive Boosting](https://mlsanity.com/paper/2210.09510/) (2022)
- [Macro-block dropout for improved regularization in training end-to-end speech recognition models](https://mlsanity.com/paper/2212.14149/) (2022)
- [Efficient Punctuation Restoration via Weighted Lookahead Scoring Method for Streaming ASR Systems](https://mlsanity.com/paper/2606.05179/) (2026)

## Abstract (arXiv)

In this paper, we review various end-to-end automatic speech recognition algorithms and their optimization techniques for on-device applications. Conventional speech recognition systems comprise a large number of discrete components such as an acoustic model, a language model, a pronunciation model, a text-normalizer, an inverse-text normalizer, a decoder based on a Weighted Finite State Transducer (WFST), and so on. To obtain sufficiently high speech recognition accuracy with such conventional speech recognition systems, a very large language model (up to 100 GB) is usually needed. Hence, the corresponding WFST size becomes enormous, which prohibits their on-device implementation. Recently, fully neural network end-to-end speech recognition algorithms have been proposed. Examples include speech recognition systems based on Connectionist Temporal Classification (CTC), Recurrent Neural Network Transducer (RNN-T), Attention-based Encoder-Decoder models (AED), Monotonic Chunk-wise Attention (MoChA), transformer-based speech recognition systems, and so on. These fully neural network-based systems require much smaller memory footprints compared to conventional algorithms, therefore their on-device implementation has become feasible. In this paper, we review such end-to-end speech recognition models. We extensively discuss their structures, performance, and advantages compared to conventional algorithms.