Tag: automatic speech recognition
Browse our exclusive articles!
Dynin-Omni: Unified Omnimodal Diffusion AI Model
Discover Dynin-Omni, the first unified omnimodal diffusion model integrating text, image, speech, and video for advanced AI understanding and generation.
JAL-Turn: Real-Time Acoustic-Linguistic Turn-Taking AI
Discover JAL-Turn, a lightweight model for real-time, robust turn-taking detection in full-duplex spoken dialogue systems using acoustic and linguistic cue...
ASR Technology for Documenting Endangered Ikema Language
Explore how automatic speech recognition aids in preserving the endangered Ikema Miyakoan language with efficient transcription and low error rates.
Abstract Compression Boosts LLM-based ASR with Context
Discover how abstract compression enhances conversational context in LLM-based ASR, improving recognition accuracy and reducing computational costs.
ASR Bias in Newcastle English: Sociolinguistic Insights
Explore how dialectal variation in Newcastle English impacts ASR accuracy, revealing social patterns and phonetic challenges in speech recognition technolo...