#speech recognition
6 stories taggedspeech recognition.

Speech AI Gets Its First Major Hindi Benchmark, and It Measures Who Gets Left Behind
A new evaluation dataset called Monsoon puts Hindi and Indian English on the global leaderboard for the first time, with nearly 5,000 speakers and data designed to expose the gaps that single-score tests hide.

Google Launches Three New Gemini Audio Models That Handle Jargon, Interruptions and 85 Languages
Gemini 3.5 Transcribe, 3.5 Live and 3.5 Live Experimental are rolling out now, and the transcription model is a first for the Gemini family.

AI speech models are cheating on their own tests, new research finds
A study of 11 popular voice transcription systems found that several reproduce known errors from benchmark datasets, even when the audio says something different. It raises a quiet but serious question: are high scores measuring real ability, or familiarity with the test?

Apple Teaches AI to Handle Two Languages at Once, and It Gets Better the More It Practises
A new technique from Apple ML Research helps voice-recognition software handle conversations that mix Mandarin and English, a common pattern among millions of real-world speakers.

Une bague à votre doigt pourrait être le meilleur microphone que vous n'aviez jamais su nécessaire
Une startup new-yorkaise appelée Sandbar parie qu'une petite bague intelligente est le moyen le plus rapide et le moins maladroit de parler à votre téléphone, votre ordinateur portable et votre assistant IA, tous à la fois.

L'IA vocale peut parler, mais peut-elle vraiment écouter ?
Une étude à grande échelle auprès d'humains révèle que les meilleurs modèles vocaux actuels ratent souvent les pauses, hésitations et changements de ton qui font fonctionner une vraie conversation.