Adobe Reveals Its New AI Tool for Editing Problematic Audio

Adobe has unveiled Project Sound Lift, an AI-powered technology that separates speech recordings into discrete tracks of voices, non-speech sounds and other background noise in video. The company describes Project Sound Lift as “a one-click solution” that leverages AI to help users easily manipulate audio recordings “across a range of scenarios” to “enhance, transform, and control speech and sound independently.” Adobe’s existing Enhance Speech technology, available in the company’s Premiere Pro editing program, has been integrated within Project Sound Lift to aid creators in producing studio-quality audio content. Continue reading Adobe Reveals Its New AI Tool for Editing Problematic Audio

YouTube AI Music Generator Mimics Stars with Their Approval

YouTube Music is testing the first in a series of AI-related music experiments. Dream Track for Shorts and the Music AI tools suite were built in collaboration with Google DeepMind’s Lyria music model to allow both original and emulative song creation. Dream Track lets users combine text prompts with the selection of a participating artist to create sound for a YouTube Short of up to 30 seconds featuring an AI simulation of the performer’s voice. Music AI can generate new music from scratch, change audio from one style or instrument to another or add vocal accompaniments. Continue reading YouTube AI Music Generator Mimics Stars with Their Approval

Google’s MusicLM AI Can Generate Tunes from Text Prompts

Google is introducing a new artificial intelligence app called MusicLM that creates music in any style or genre based on text prompts and can translate a whistled melody or casually hummed snipped into instrument sounds. TechCrunch calls the technology “impressive” but says the Alphabet company “fearing the risks, has no immediate plans to release it,” in recognition of the controversy surrounding AI models trained using copyrighted material. MusicLM was created using a dataset of 280,000 musical hours, resulting in the ability to generate minutes-long songs of “significant complexity.” Continue reading Google’s MusicLM AI Can Generate Tunes from Text Prompts

Spotify’s Soundtrap Expands its Free Toolset for Podcasters

Acquired by Spotify in 2017, cloud-based audio recording studio Soundtrap just expanded its free tier for podcasters, now offering access to an unlimited number of projects and 2,210 loops. All creators using Soundtrap will now have unlimited free storage for podcasts and songs. Founded in 2012, the Swedish-based company has offered four subscription tiers, ranging from $10 to $17 per month, all supporting an unlimited number of projects, 550 instruments and 4,100 loops. Soundtrap’s free tier previously limited users to five projects and 900 loops. The number of available instruments will remain the same. Continue reading Spotify’s Soundtrap Expands its Free Toolset for Podcasters

Splice Fosters Music Collaboration with its New Cloud Service

More than 100,000 music producers and artists are reportedly now using a cloud-based service called Splice to produce music tracks on-the-go. Users store their tracks in the cloud and provide collaborators with access to edit the tracks with compatible music editing software such as GarageBand or Ableton Live. Splice’s technology helps manage how each user has tweaked the tracks. The startup, which officially launched in September, makes money by selling add-ons for music editing software. Continue reading Splice Fosters Music Collaboration with its New Cloud Service

Engineers Developing Emotion-Based Video Game Controller

Stanford engineers have created the next step in interactive gaming — a video game controller that can sense a player’s emotions. The handheld game controller can monitor a player’s brain activity to decipher when a user is extremely engaged or bored, which could trigger zombies or another element of the game to be thrown at them to catch their attention. Gregory Kovacs, a professor of electrical engineering at Stanford, created a prototype controller in his lab in collaboration with Texas Instruments. Continue reading Engineers Developing Emotion-Based Video Game Controller

Intel Confirms Purchase of Wearables Startup Basis Science

Intel confirmed yesterday that it has acquired Basis Science, a San Francisco-based startup that makes a $199 health-tracking wristband known as the Basis Band. The device — which tracks sleep, heart rate, calories and steps — syncs with iOS and some Android devices via Bluetooth. Up to this point, the Basis Band device has used Texas Instruments chips. Intel has bigger plans than merely supplying processors, and the acquisition could be the first step toward entering the wearables market more directly. Continue reading Intel Confirms Purchase of Wearables Startup Basis Science