Tag

Speech Synthesis

All articles tagged with #speech synthesis

technology18 days ago•2 min saved

Linux Set to Axe Obsolete ISA DoubleTalk Driver in 7.2

Linux is moving to retire the outdated DTLK ISA speech-synthesizer driver (Double Talk) as part of the 7.2 kernel cycle. The driver hasn’t seen meaningful work in years, and the same hardware is supported by a separate accessibility path (Speakup), making the legacy driver largely unused. The commit argues removing it will reduce future maintenance, noting RC Systems’ DoubleTalk page remains outdated and the hardware should be retired with Linux 7.2.

via Phoronix|

#drivers #isa #kernel

technology1 year ago•2 min saved

Proton Experimental Enhances Steam Deck with Speech Synthesis and Game Fixes

Valve's Proton Experimental has been updated to include initial speech synthesis support and various game fixes for Steam Deck and Linux. The update also simplifies modding by allowing most mods to be extracted next to the game executable without additional steps. This change, along with previous updates like NVIDIA Optical Flow API support, enhances the gaming experience on Linux. Proton 9.0-4 is also in testing as the next stable version.

via GamingOnLinux|

#game-modding #linux-gaming #proton

science-and-technology2 years ago•32 min saved

"The Pioneering MIT Scientist Behind Stephen Hawking's Famous Voice"

Stephen Hawking's iconic computer-generated voice, used for the last three decades of his life, was a reproduction of the real-life voice of pioneering scientist Dennis Klatt, who developed state-of-the-art computer systems for speech synthesis. Klatt's speech synthesizers, including the popular Perfect Paul, marked a turning point in speech synthesis by using a mathematical model to represent the human vocal tract and produce highly intelligible speech. This approach revolutionized speech synthesis technology and laid the foundation for modern AI-driven speech systems like Siri and Alexa.

via Big Think|

#dectalk #dennis-klatt #perfect-paul

artificial-intelligence2 years ago•2 min saved

OpenAI's ChatGPT Enhances AI Capabilities to Speak, Listen, and Process Images

OpenAI has announced an update to its ChatGPT AI models, enabling them to analyze images and engage in verbal conversations. The image recognition feature allows users to upload images for conversation, while the speech synthesis feature enables back-and-forth spoken interactions with ChatGPT. OpenAI plans to roll out these features to Plus and Enterprise subscribers in the next two weeks. The company claims that image recognition can be used for various everyday applications, and users can circle parts of the image to focus on. Technical details of the multimodal functionality are not disclosed, but it is speculated that OpenAI may use CLIP to align image and text representations. The voice synthesis feature offers five synthetic voices and is supported by OpenAI's Whisper speech recognition system.

via Ars Technica|

#ai-models #artificial-intelligence #chatgpt

technology2 years ago•2 min saved

"Master the Art of AI Mimicry: Train Your AI to Perfectly Emulate Your Voice"

AI voices are becoming increasingly prevalent on the internet, with AI systems capable of generating believable speech in various languages and voices. The Verge conducted an experiment using different AI bots to replicate the voice of one of their hosts, highlighting the rapid advancements in this technology. While the potential applications are vast, such as AI-generated music and voiceovers, ethical concerns arise regarding the responsible use of these tools and the potential for deepfakes. The need to navigate these issues becomes increasingly urgent as the technology continues to improve.

via The Verge|

#ai-voices #artificial-intelligence #deepfakes

health3 years ago•0 min saved

Voice banking helps restore speech for ALS patients using AI.

AI-powered voice banking is helping people with ALS to preserve their voices before they lose the ability to speak. The technology uses machine learning algorithms to create a synthetic voice that sounds like the person's natural voice. This assistive technology is providing a way for people with ALS to communicate with loved ones even after they lose the ability to speak.

via The Washington Post|

#ai #als #assistive-technology