#speech recognition
Speech Recognition: 6 AI articles covering speech recognition news, analysis, and research
Articles
Nirva Raises $33M for a Pendant That Only Listens to Youβ8
Nirva raises $33M for a lightweight AI pendant that passively listens only to the wearer, blending fashion with privacy-focused ambient AI.
Iceland's Treble Raises $18M to Scale Voice AI Simulation Platformβ9
Iceland's Treble raises $18M to scale its voice AI simulation platform, helping companies like Amazon and Logitech test and train audio models.
How AI Receptionists Work: The Architecture Behind AI Phone Agentsβ8
Explore the architecture behind AI phone agentsβfrom speech recognition to CRM APIsβand how call flows, routing, and context work together.
Measuring Benchmark Optimization in Speech Recognitionβ9
Explore key metrics and techniques for speech recognition benchmark optimization, from WER to real-time efficiency, plus real-world deployment implications.
PolyAI's Dialog-RSN-1: An Audio-Native Dialog Model Combiningβ8
PolyAI's Dialog-RSN-1 fuses turn-taking, speech recognition, and response generation into one audio-native model, cutting latency by up to 37% in live calls.
Best Open Speech Recognition (ASR) Models in 2026: WER,β7
Compare 2026's top open ASR models: Cohere Transcribe, Whisper Large-v3, Nvidia NeMo Canary, Meta SeamlessM4T-v2 on WER, language support, latency, and licenses...