On the Impact of Quantization and Pruning of Self-Supervised Speech Models for Downstream Speech Recognition Tasks "In-the-Wild''

no code implementations • 25 Sep 2023 • Arthur Pimentel, Heitor Guimarães, Anderson R. Avila, Mehdi Rezagholizadeh, Tiago H. Falk

Recent advances with self-supervised learning have allowed speech recognition systems to achieve state-of-the-art (SOTA) word error rates (WER) while requiring only a fraction of the labeled training data needed by its predecessors.

Data Augmentation Model Compression +4

An Exploration into the Performance of Unsupervised Cross-Task Speech Representations for "In the Wild'' Edge Applications

no code implementations • 9 May 2023 • Heitor Guimarães, Arthur Pimentel, Anderson Avila, Mehdi Rezagholizadeh, Tiago H. Falk

Later, these representations serve as input to downstream models to solve a number of tasks, such as keyword spotting or emotion recognition.

Emotion Recognition intent-classification +2