Voice casting has always been challenging in the multimedia industry. Recent research shows that voice casting can be done with the help of speaker recognition methods. In this paper, the first datase...

Voice casting is one of the most crucial aspects of dubbing and localization, which consists of adapting audio-visual content from one language and culture to another. Dubbing is widely used in variou...

Advances in deep learning have led to significant progress in the field of speech processing, particularly in applications such as speaker recognition systems (SRSs). Additional information such as ge...

A new study finds that the left posterior inferior frontal cortex activates within 100 milliseconds during reading, playing a critical, early role in turning text into speech, challenging traditional models that assumed a slower, step-by-step process.

Voxtral – Frontier open source speech understanding models (mistral.ai) 07-15  ↑ 103 HN Points

We present Voxtral Mini and Voxtral Small, two multimodal audio chat models. Voxtral is trained to comprehend both spoken audio and text documents, achieving state-of-the-art performance across a diverse range of audio benchmarks, while preserving strong text capabilities. Voxtral Small outperforms a number of closed-source models, while being small enough to run locally. A 32K context window enables the model to handle audio files up to 40 minutes in duration and long multi-turn conversations. We also contribute three benchmarks for evaluating speech understanding models on knowledge and trivia. Both Voxtral models are released under Apache 2.0 license.

Voice experiments in people with epilepsy have helped trace the circuit of electrical signals in the brain that allow its hearing center to sort out background sounds from their own voices.