An End-to-End Neural Network for Image-to-Audio Transformation
Not on the map. Why?
Abstract (arXiv)
This paper describes an end-to-end (E2E) neural architecture for the audio rendering of small portions of display content on low resource personal computing devices. It is intended to address the problem of accessibility for vision-impaired or vision-distracted users at the hardware level. Neural image-to-text (ITT) and text-to-speech (TTS) approaches are reviewed and a new technique is introduced to efficiently integrate them in a way that is both efficient and back-propagate-able, leading to a non-autoregressive E2E image-to-speech (ITS) neural network that is efficient and trainable. Experimental results are presented showing that, compared with the non-E2E approach, the proposed E2E system is 29% faster and uses 19% fewer parameters with a 2% reduction in phone accuracy. A future direction to address accuracy is presented.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 16 of its 23 references that are in the map. First posted on arXiv 10 Mar 2023.
Builds on
16 of 23 references.
References · 16
- 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
- 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
- 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 717
- 2016Synthetic Data for Text Localisation in Natural Imagescited by 396
- 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 273
- 2014Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognitioncited by 214
- 2014Reading Text in the Wild with Convolutional Neural Networkscited by 122
- 2016Robust Scene Text Recognition with Automatic Rectificationcited by 121
- 2020End-to-End Adversarial Text-to-Speechcited by 77
- 2020Parallel Tacotron: Non-Autoregressive and Controllable TTScited by 49
- 2021One TTS Alignment To Rule Them Allcited by 47
- 2021PortaSpeech: Portable and High-Quality Generative Text-to-Speechcited by 47
4 more
- 2021Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modelingcited by 31
- 2019Aggregation Cross-Entropy for Sequence Recognitioncited by 22
- 2019HBONet: Harmonious Bottleneck on Two Orthogonal Dimensionscited by 13
- 2021Revisiting Classification Perspective on Scene Text Recognitioncited by 5
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.