Sketching With Your Voice: "Non-Phonorealistic" Rendering of Sounds via Vocal Imitation

2024/09/20 by Matthew Caren, Kartik Chandra, Joshua B. Tenenbaum +3 · 1 voice
Computer Science · Engineering · Psychology · #Artificial intelligence #Auditory feedback #Computer science #Human Motion and Animation #Human voice #Imitation #Music Technology and Sound Studies #Music and Audio Processing #Psychology #Rendering (computer graphics) #Salient #Speech recognition #Vocal tract

paper · pdf · doi:10.1145/3680528.3687679

openalex publication_date 2024/12/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

Abstract

SA Conference Papers ’24, December 03–06, 2024, Tokyo, Japan

Discussions

• Graphics has long studied how to make: (1) realistic images 📷 (2) non-photorealistic images ✍️ (3) realistic sounds 🎤 What about (4) "non-phono-realistic" sounds? What could that even mean? Next [bsky, 45 points, 2 comments]

Related

• Sketch2Sound: Controllable Audio Generation via Time-Varying Signals and Sonic Imitations
• CartoonSing: Unifying Human and Nonhuman Timbres in Singing Generation
• Polyphonic overtone singing: An acoustic and physiological (MRI) analysis and a first-person description of a unique mode of singing
• Empowering Communication: Speech Technology for Indian and Western Accents through AI-powered Speech Synthesis
• The NPU-HWC System for the ISCSLP 2024 Inspirational and Convincing Audio Generation Challenge