CLSP Fall Seminar Series: Tatiana Likhomanenko

Description

Tatiana Likhomanenko, a research scientist with the machine learning research team at Apple, will give a talk titled "Efficient Speech Processing" for the Center for Language and Speech Processing.

Abstract:

This talk will cover three different directions of my research journey in the speech domain: recognition, generation, and privacy. We will start with self-training algorithms that have recently emerged as a powerful strategy for semi-supervised learning in large-scale speech recognition. We will discuss different aspects of self-training to make it simple and resource efficient. Then we will delve into the language modeling for speech recognition where I show that at the proper scale error correction models outperform conventional language models. Next point of discussion will be the joint modeling of text-to-speech and speech-to-text with the help of a simple tokenization scheme. Finally, I discuss how speech recognition systems can be trained with differential privacy and federated learning.