2 papers
eess.AS2024
Fine-Grained and Interpretable Neural Speech Editing
Max Morrison, Cameron Churchwell, Nathan Pruyne +1
Fine-grained editing of speech attributes$\unicode{x2014}$such as prosody (i.e., the pitch, loudness, and phoneme durations), pronunciation, speaker identity, and formants$\unicode…
eess.AS2024
High-Fidelity Neural Phonetic Posteriorgrams
Cameron Churchwell, Max Morrison, Bryan Pardo
A phonetic posteriorgram (PPG) is a time-varying categorical distribution over acoustic units of speech (e.g., phonemes). PPGs are a popular representation in speech generation due…