Speech Large Language Models
PulseAugur coverage of Speech Large Language Models — every cluster mentioning Speech Large Language Models across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New LOGIC framework improves Speech LLM entity recognition
Researchers have developed a new framework called LOGIC (Logit-Space Integration for Contextual Biasing) to improve how Speech Large Language Models (Speech LLMs) handle new and domain-specific entities. Unlike traditio…
-
Nuha-Speech initiative builds Arabic Speech LLMs with 1.5M+ QA samples
Researchers have introduced Nuha-Speech, a project aimed at developing general-purpose Arabic Speech Large Language Models (speech-LLMs). This initiative addresses the underrepresentation of Arabic in multilingual speec…
-
VoxZip framework slashes audio LLM KV cache needs by 20x
Researchers have developed VoxZip, a novel two-stage framework designed to compress the KV cache for long-context audio inference in Speech Large Language Models. This method uses Automatic Speech Recognition (ASR) tran…
-
New gaslighting attacks reveal 24% accuracy drop in speech LLMs
Researchers have developed a new method to test the vulnerability of speech-based large language models (LLMs) to manipulative prompts, termed "gaslighting attacks." These attacks employ five strategies—Anger, Cognitive…