Fusion Segment Transformer
Detects AI-generated music from structure and MERT
None defined yet.
Detects AI-generated music from structure and MERT
Music emotion as mood tags and valence-arousal
Multilingual speech synthesis and voice cloning
Reconstruct or restyle MIDI with a variational model
SpeechBrain Tacotron2 TTS on LJSpeech
Turns rhythm and timbre prompts into drum parts
RemFX detects and removes audio effects
Text-to-music with chord and rhythm control
ByteDance MegaTTS 3 zero-shot voice cloning
Splits a drum mix into five individual drum stems
Tags sounds across 527 AudioSet classes
Two-stage U-Net for gramophone denoising
Generates a text caption describing the audio
Detects beat and downbeat positions in music
Lightweight AudioSet sound event tagging on CPU
Scores audio aesthetics and production quality
Fills a gap in audio with a diffusion model
Restores lossy MP3 audio toward near-lossless quality
Generates accompaniment for a vocal or lead
Spectral-gating noise reduction
ITU-R BS.1770-4 loudness and range metering
Emulates an LA-2A compressor with a small TCN
OpenAI Whisper speech-to-text transcription
Restores degraded speech of any kind