# Compression of end-to-end non-autoregressive image-to-speech system for low-resourced devices

arXiv: https://arxiv.org/abs/2312.00174 · HTML: https://mlsanity.com/paper/2312.00174/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 26 references that are in the map.
- First posted on arXiv 30 Nov 2023.

## Builds on (most cited first, 23 of 23)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://mlsanity.com/paper/2004.02984/) (2020)
- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [Q8BERT: Quantized 8Bit BERT](https://mlsanity.com/paper/1910.06188/) (2019)
- [TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation](https://mlsanity.com/paper/1805.04699/) (2018)
- [Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition](https://mlsanity.com/paper/1406.2227/) (2014)
- [Vision Transformer for Fast and Efficient Scene Text Recognition](https://mlsanity.com/paper/2105.08582/) (2021)
- [PortaSpeech: Portable and High-Quality Generative Text-to-Speech](https://mlsanity.com/paper/2109.15166/) (2021)
- [VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature](https://mlsanity.com/paper/2204.00768/) (2022)
- [JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech](https://mlsanity.com/paper/2203.16852/) (2022)
- [HBONet: Harmonious Bottleneck on Two Orthogonal Dimensions](https://mlsanity.com/paper/1908.03888/) (2019)
- [Source-Filter HiFi-GAN: Fast and Pitch Controllable High-Fidelity Neural Vocoder](https://mlsanity.com/paper/2210.15533/) (2022)
- [Compact Speaker Embedding: lrx-vector](https://mlsanity.com/paper/2008.05011/) (2020)
- [An End-to-End Neural Network for Image-to-Audio Transformation](https://mlsanity.com/paper/2303.06078/) (2023)
- [Fast and small footprint Hybrid HMM-HiFiGAN based system for speech synthesis in Indian languages](https://mlsanity.com/paper/2302.06227/) (2023)

## Abstract (arXiv)

People with visual impairments have difficulty accessing touchscreen-enabled personal computing devices like mobile phones and laptops. The image-to-speech (ITS) systems can assist them in mitigating this problem, but their huge model size makes it extremely hard to be deployed on low-resourced embedded devices. In this paper, we aim to overcome this challenge by developing an efficient endto-end neural architecture for generating audio from tiny segments of display content on low-resource devices. We introduced a vision transformers-based image encoder and utilized knowledge distillation to compress the model from 6.1 million to 2.46 million parameters. Human and automatic evaluation results show that our approach leads to a very minimal drop in performance and can speed up the inference time by 22%.