Technology ❯ Artificial Intelligence

Speech Processing

Automatic Speech Recognition Animal Communication Voice Synthesis Accent Modification Accent Conversion Acoustic Models Accent Control Question Answering Systems Hierarchical Frame Querying Emotion Recognition Transcription Technology Real-Time Translation Speech Synthesis Speech-Language Models Acoustic Representations Real-Time Communication Speaker Diarization Speech Generation Audio-Visual Speech Separation Speech-to-Text and Text-to-Speech

Meta Launches Muse Voice Transcribe for Real‑Time Speech Recognition

Live on the Meta Model API, Muse powers dictation in Meta AI for Mac using adaptive delay to balance latency and accuracy.

Apple and Tel-Aviv University Detail PCG Method That Accelerates AI Speech by About 40%

Nvidia Open-Sources Alpamayo‑R1 to Advance Explainable Autonomy at NeurIPS