Prosody Generation for Speech-to-Speech Translation

62 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Direct Speech-to-Speech Translation With Discrete Units (2021, background): “Studies on TTS for S2ST focus more on synthesizing the para-linguistic information transferred from the source speech, such as prosody [18, 19] and word-level emphasis [20].”
Direct speech-to-speech translation with a sequence-to-sequence model (2019, methodology): “For synthesis, [9] used unsupervised clustering to find F0-based prosody features and transfer intonation from source speech and target.”
Speech Translation and the End-to-End Promise: Taking Stock of Where We Are (2020, background): “, 2009) beneficial for speech outputs, given that human listeners are naturally able to repair disfluencies (Lickley, 1994)? Further examples that need more exploration are prosody transfer (Aguero et al., 2006) and models that directly translate speech-to-speech (Jia et al.”
Exploiting Acoustic and Syntactic Features for Prosody Labeling in a Maximum Entropy Framework (2007, methodology): “Parametric approaches either restrict the variants of prosody by definition or automatically learn prosodic patterns from data (Agüero et al., 2006).”
Toward Expressive Speech Translation: A Unified Sequence-to-Sequence LSTMs Approach for Translating Words and Emphasis (2017, background): “Emphasis is manifested by changing many acoustic features including F0, power, and duration [9, 10].”