ML-SUPERB
Emerging13papers using it
2023first seen
The ML-SUPERB dataset is a benchmark used to evaluate multilingual automatic speech recognition (ASR) performance, specifically focusing on the effectiveness of discrete token representations in improving model accuracy.
Papers using ML-SUPERB (13)
- How to Learn a New Language? An Efficient Solution for Self-Supervised
Learning Models Unseen Languages Adaption in Low-Resource ScenarioMultilingual Speech Recognition Using Discrete Tokens with a Two-step Training StrategyFindings of the 2023 ML-SUPERB Challenge: Pre-Training and Evaluation
over More Languages and BeyondmHuBERT-147: A Compact Multilingual HuBERT ModelCA-SSLR: Condition-Aware Self-Supervised Learning Representation for
Generalized Speech ProcessingML-SUPERB: Multilingual Speech Universal PERformance BenchmarkAre Paralinguistic Representations all that is needed for Speech Emotion
Recognition?SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech RecognitionSSHR: Leveraging Self-supervised Hierarchical Representations for
Multilingual Automatic Speech RecognitionEvaluating Self-supervised Speech Models on a Taiwanese Hokkien CorpusTowards Robust Speech Representation Learning for Thousands of LanguagesCodec-ASR: Training Performant Automatic Speech Recognition Systems with
Discrete Speech RepresentationsFusion of Discrete Representations and Self-Augmented Representations
for Multilingual Automatic Speech Recognition