SpecAugment: A New Data Augmentation Method for Automatic Speech Recognition – Google Research Blog
ai.googleblog.com · 1,396 words · saved by 1 readers
Posted by Daniel S. Park, AI Resident and William Chan, Research Scientist
SpecAugment: A New Data Augmentation Method for Automatic Speech Recognition Skip to main content SpecAugment: A New Data Augmentation Method for Automatic Speech Recognition April 22, 2019 Posted by Daniel S. Park, AI Resident and William Chan, Research Scientist Quick links Share Copy link × Automatic Speech Recognition (ASR), the process of taking an audio input and transcribing it to text, has benefited greatly from the ongoing development of deep neural networks . As a result, ASR has become ubiquitous in many modern devices and products, such as Google Assistant, Google Home and YouTube.
saved by
related reading
- Audio Deep Learning Made Simple: Automatic Speech Recognition (ASR), How it Works | Towards Data Sciencetowardsdatascience.com
- Crossing the uncanny valley of conversational voice | Sesamesesame.com
- [2105.11084] Unsupervised Speech Recognitionarxiv.org
- Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
- Silent speech with ultrasound — Alephalephneuro.com
- Audio Deep Learning Made Simple: Sound Classification, step-by-step | Towards Data Sciencetowardsdatascience.com
- WaveNetdeepmind.com
- Fast Inference from Transformers via Speculative Decodingarxiv.org
- Efficient Training of Language Models to Fill in the Middle | PDFarxiv.org
- 2206.14483arxiv.org
- 2206.14483.pdfarxiv.org
- radford2018improving.pdfcs.ubc.ca