Artificial intelligence was built to process data, not to think like us. Yet a growing body of research is finding that the internal workings of advanced language and speech models are starting to ...

Postdoctorate Viet Anh Trinh led a project within Strand 1 to develop a novel neural network architecture that can both recognize and generate speech. He has since moved on from iSAT to a role at ...

Apple researchers figured out a way to speed up AI speech generation from text without sacrificing audio quality or breaking intelligibility.

Recent advances in artificial intelligence have profoundly transformed the field of speech recognition and language processing. Contemporary methods now harness deep neural networks and sophisticated ...

Talking to yourself feels deeply human. Inner speech helps you plan, reflect, and solve problems without saying a word.

By tracking brain activity as people listened to a spoken story, researchers found that the brain builds meaning step by step ...

On Tuesday, Meta announced SeamlessM4T, a multimodal AI model for speech and text translations. As a neural network that can process both text and audio, it can perform text-to-speech, speech-to-text, ...

Microsoft has introduced a new AI model that, it says, can process speech, vision, and text locally on-device using less compute capacity than previous models. Innovation in generative artificial ...

Exploring uses for artificial intelligence (AI) machine learning is de rigueur, and large language models (LLMs) are having their moment in the spotlight. Last year, LLMs were used in a variety of ...

Large language models (LLMs) such as GPT-4o and other modern state-of-the-art generative models like Anthropic’s Claude, Google's PaLM and Meta's Llama have been dominating the AI field recently.