Speech recognition without heavy software or energy-hungry processors: researchers at the University of Twente, together with IBM Research Europe and Toyota Motor Europe, present a completely new ...

British authorities have ramped up the use of facial recognition, artificial intelligence and internet regulation to address crime and other issues, stoking concerns of surveillance overreach. British ...

On September 8, 2025, Alibaba’s Qwen team introduced Qwen3-ASR Flash, an automatic speech recognition (ASR) system covering 11 languages — as well as multiple dialects and accents — and a range of ...

In today’s voice-first world, it’s not enough for systems to simply hear what users say. They need to understand it with precision. In high-stakes environments like healthcare, finance, or enterprise ...

The Allen Institute for AI (AI2) has released OLMoASR, a suite of open automatic speech recognition (ASR) models that rival closed-source systems such as OpenAI’s Whisper. Beyond just releasing model ...

2023-07-26: We have released our training recipe for real-time AV-ASR, see here. 2023-06-16: We have released our training recipe for AutoAVSR, see here. 2023-03-27: We have released our AutoAVSR ...

Mistral AI has released Voxtral, a family of open-weight models—Voxtral-Small-24B and Voxtral-Mini-3B—designed to handle both audio and text inputs. Built on top of Mistral’s language modeling ...

Speech recognition models, predominantly trained on standard speech, often exhibit lower accuracy for individuals with accents, dialects, or speech impairments. This disparity is particularly ...

These days, people can have natural conversations with their phones as if they were chatting with a friend. That’s thanks to the rapid evolution of voice recognition AI (artificial intelligence) ...

What if the race to perfect AI speech recognition wasn’t just about accuracy but also speed and usability? In a world where audio-to-text transcription powers everything from virtual meetings to ...

ABSTRACT: Anomaly detection in complex crowd scenes is a challenging task due to the inherent variability in crowd behaviors, interactions, and scales. This paper proposes a novel hybrid model that ...