Decagon, which builds AI-powered voice experiences, saw a 30% improvement in transcription accuracy using OpenAI’s speech recognition model.

Combining audio, images, and text helps the model better understand speech context. To improve its performance, we fine-tune a strong language model by blending unsupervised learning with multimodal ...

Howard University and Google are teaming up to change speech recognition for Black Americans through a partnership called “Project Elevate Black Voices.” ...

Balls of human brain cells linked to a computer have been used to perform a very basic form of speech recognition. The hope is that such systems will use far less energy for AI tasks than silicon ...