SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities
This provides a standardized benchmark for researchers in speech processing to evaluate pre-trained models more holistically, though it is incremental over the original SUPERB.
The paper tackles the lack of consistent evaluation for pre-trained speech models by introducing SUPERB-SG, a benchmark that enhances task diversity and difficulty to assess semantic and generative capabilities, showing it effectively evaluates model generalizability with limited supervision.
Transfer learning has proven to be crucial in advancing the state of speech and natural language processing research in recent years. In speech, a model pre-trained by self-supervised learning transfers remarkably well on multiple tasks. However, the lack of a consistent evaluation methodology is limiting towards a holistic understanding of the efficacy of such models. SUPERB was a step towards introducing a common benchmark to evaluate pre-trained models across various speech tasks. In this paper, we introduce SUPERB-SG, a new benchmark focused on evaluating the semantic and generative capabilities of pre-trained models by increasing task diversity and difficulty over SUPERB. We use a lightweight methodology to test the robustness of representations learned by pre-trained models under shifts in data domain and quality across different types of tasks. It entails freezing pre-trained model parameters, only using simple task-specific trainable heads. The goal is to be inclusive of all researchers, and encourage efficient use of computational resources. We also show that the task diversity of SUPERB-SG coupled with limited task supervision is an effective recipe for evaluating the generalizability of model representation.