Topic: audio

8 stories found

Thursday, October 29, 2026

industry24

Block Unveils Dessa, a Full-Duplex Speech Model Trained Only on Speech

Block's AI lab introduced Dessa, a full-duplex speech model trained solely on human conversation audio and designed to run locally on a MacBook Pro M4 Max. The release highlights advancements in privacy-focused AI models that process and generate speech directly from local devices without cloud dependency.

marktechpost.com↗

Wednesday, October 28, 2026

releases54

Ollama releases: v0.40.13

Ollama released version 0.40.13 of its LFM3 models, enabling text-to-speech functionality on both Linux and Windows in addition to existing platforms, expanding accessibility for users across different operating systems. This update is significant as it broadens the user base and compatibility of Liquid AI's advanced language models.

github.com↗
research40

Lipi-Ghor: A Large-Scale, Diarized, Multi-Domain Bengali Speech Corpus and a Scalable Pipeline for Building It

A new large-scale corpus called Lipi-Ghor has been created for Bengali speech, addressing the under-resourcing issue in spoken language research by providing extensive, diarized, multi-domain audio. This corpus is significant as it offers a substantial dataset for improving Bengali speech recognition technologies.

arxiv.org↗
industry24

Meet Google DeepMind’s Genie 4: Real-Time World Model With Native Audio

Google DeepMind unveiled Genie 4, a real-time world model with native audio and advanced features like live dialogue and text steering. This release is significant as it enhances the capabilities of simulated environments for research and development.

marktechpost.com↗

Tuesday, October 27, 2026

research40

Whispering Wisely: Smart Subset Selection for ASR Fine-Tuning

Researchers propose a smart subset selection method for fine-tuning ASR models like Whisper, reducing the need for extensive transcribed data and lowering costs. This approach is crucial as it enhances accessibility and efficiency in improving speech recognition quality without the high expense of full dataset fine-tuning.

arxiv.org↗

Saturday, October 24, 2026

releases54

Ollama releases: v0.40.11

Ollama v0.40.11 adds speech functionality on macOS, allowing text-to-speech generation during model runs and supporting audio streaming via the API, enhancing accessibility and user experience. This update is significant as it broadens Ollama's capabilities, making it more versatile for various applications.

github.com↗

Wednesday, August 12, 2026

ai_labsπŸŽ™ Podcast52

#500 – Khabib Nurmagomedov: Dagestan, MMA, UFC, Islam, Conor, Fedor & Football

Khabib Nurmagomedov, known for his undefeated MMA career with a 29-0 record, spoke exclusively in Russian about his life and fighting legacy, including his Dagestani roots and religious beliefs, which are translated into English subtitles for global audiences. This conversation highlights the cultural and personal aspects behind one of MMA's greatest fighters, emphasizing his identity and influence beyond the octagon.

lexfridman.com↗

🌿 That's all for now. Come back tomorrow.

8 of 8 items shown. Sources: 169 days indexed.