5 citations · 6 across the 5 of their papers we have counts for
Showing 2021Show all
3 papers · 1 filter
cs.CL2021★ 5 cited
Grapheme-to-Phoneme Transformer Model for Transfer Learning Dialects
Eric Engelhart, Mahsa Elyasi, Gaurav Bharaj
Grapheme-to-Phoneme (G2P) models convert words to their phonetic pronunciations. Classic G2P methods include rule-based systems and pronunciation dictionaries, while modern G2P sys…
cs.SD2021★ 1 cited
Flavored Tacotron: Conditional Learning for Prosodic-linguistic Features
Mahsa Elyasi, Gaurav Bharaj
Neural sequence-to-sequence text-to-speech synthesis (TTS), such as Tacotron-2, transforms text into high-quality speech. However, generating speech with natural prosody still rema…
cs.SD2021
Generalized Spoofing Detection Inspired from Audio Generation Artifacts
Yang Gao, Tyler Vuong, Mahsa Elyasi +2
State-of-the-art methods for audio generation suffer from fingerprint artifacts and repeated inconsistencies across temporal and spectral domains. Such artifacts could be well capt…