Machine Learning and Speech: A Review of FPF’s Digital Data Flows Masterclass
Retrieved on:
Friday, December 18, 2020
Authors: Hunter Dorwart, Caroline Hopland, and Rob van Eijk On Wednesday, December 9, 2020, FPF hosted a Digital Data Flows Masterclass on Machine Learning and Speech.
Key Points:
- Authors: Hunter Dorwart, Caroline Hopland, and Rob van Eijk On Wednesday, December 9, 2020, FPF hosted a Digital Data Flows Masterclass on Machine Learning and Speech.
- The masterclass on Machine Learning and Speech is the first masterclass of a new series after completing the VUB-FPF Digital Data Flows Masterclass series with eight topics.
- Dr. Prem Natarajan (VP, Alexa AI-Natural Understanding) guides us through the intricacies of Machine Learning in the context of voice assistants.
- The presenters explored the differences between supervised, semi-supervised, and unsupervised machine learning (ML) and the impact of these recent technical developments on machine translation and speech recognition technologies.
- Machine Translation An Introduction As a sub-field of computational linguistics, machine translation studies the use of software to translate text or speech from one language to another.
- Deep learning requires very large datasets and paired translation examples (e.g., English to French), which might not exist for certain languages.
- Even when there is a large pool of data, sentences often have multiple correct translations, which poses additional problems for machine learning.
- How to Train a Machine Learning Model Supervised, Unsupervised, and Semi-Supervised Learning Training neural models with limited translation data poses multiple problems (see also, Figure 1).
- Finally, semi-supervised learning combines elements of both supervised and unsupervised learning and is the primary training method for translation models.
- From a high level perspective, neural models employing machine learning produce more fluent translations than older statistical models.
- Machine Learning and Speech Many of the lessons learned in recent advancements of machine translation also apply to the area of speech recognition.
- Yet while the idea of machine learning through neural networking became widespread in the discipline, the lack of computing power and data inhibited its development.
- Advancements in Training Models Indeed, present speech recognition technology utilizes a range of learning methods at the cutting edge of deep learning, including active learning, transfer learning, semi-supervised learning, learning to paraphrase, self-learning, and teaching AI.
- Transfer learning data takes data rich domains and finds ways to transfer learning to new domains that lack corresponding data.
- Digital Data Flows Masterclass Archive The Digital Data Flows Masterclass Archive with the recordings and resources for previous classes can be accessed here.