SoundStorm: Efficient parallel audio generation
Who said what? Recorder's on-device solution for labeling speakers
AudioLM: a Language Modeling Approach to Audio Generation
Music Conditioned 3D Dance Generation with AIST++
SoundStream: An End-to-End Neural Audio Codec
Applying Advanced Speech Enhancement in Cochlear Implants
LEAF: A Learnable Frontend for Audio Classification
Lyra: A New Very Low-Bitrate Codec for Speech Compression
Navigating Recorder Transcripts Easily, with Smart Scrolling
The Machine Learning Behind Hum to Search
Improving Audio Quality in Duo with WaveNetEQ
