Picture for Karen Livescu

Karen Livescu

Shammie

SHuBERT: Self-Supervised Sign Language Representation Learning via Multi-Stream Cluster Prediction

Add code
Nov 25, 2024
Viaarxiv icon

Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks

Add code
Nov 08, 2024
Viaarxiv icon

Speech Recognition for Analysis of Police Radio Communication

Add code
Sep 17, 2024
Figure 1 for Speech Recognition for Analysis of Police Radio Communication
Figure 2 for Speech Recognition for Analysis of Police Radio Communication
Figure 3 for Speech Recognition for Analysis of Police Radio Communication
Figure 4 for Speech Recognition for Analysis of Police Radio Communication
Viaarxiv icon

Approaching Deep Learning through the Spectral Dynamics of Weights

Add code
Aug 21, 2024
Viaarxiv icon

Towards Robust Speech Representation Learning for Thousands of Languages

Add code
Jul 02, 2024
Viaarxiv icon

On the Evaluation of Speech Foundation Models for Spoken Language Understanding

Add code
Jun 14, 2024
Viaarxiv icon

On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models

Add code
Jun 13, 2024
Viaarxiv icon

DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding

Add code
Jun 13, 2024
Figure 1 for DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding
Figure 2 for DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding
Figure 3 for DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding
Figure 4 for DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding
Viaarxiv icon

ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets

Add code
Jun 12, 2024
Viaarxiv icon

Self-Supervised Speech Representations are More Phonetic than Semantic

Add code
Jun 12, 2024
Figure 1 for Self-Supervised Speech Representations are More Phonetic than Semantic
Figure 2 for Self-Supervised Speech Representations are More Phonetic than Semantic
Figure 3 for Self-Supervised Speech Representations are More Phonetic than Semantic
Figure 4 for Self-Supervised Speech Representations are More Phonetic than Semantic
Viaarxiv icon