RAD-TTS: Parallel Flow-Based TTS with Robust Alignment Learning and Diverse Synthesis

How researchers see this paper

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

Audiobox: Unified Audio Generation with Natural Language Prompts (2023, methodology): “Instead, we represent transcript with raw characters, including punctuation and with true cases, and utilize the SeamlessM4T v2 multilingual char-to-unit forced aligner presented in Seamless Communication (2023) adapted from RAD-TTS (Shih et al., 2021).”
Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidance (2021, methodology): “…of the autoregressive models, flow-based generative models (Kingma & Dhariwal, 2018) and feed-forward models have been proposed for text-to-mel-spectrogram models (Ren et al., 2019; 2021; Kim et al., 2020; Shih et al., 2021) and vocoders (Oord et al., 2018; Prenger et al., 2019; Kim et al., 2019).”
JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech (2022, methodology): “Note that we also apply beta-binomial alignment prior as in [18], [26] which multiplies 2d static prior to A soft to accelerate the alignment learning by making the near-diagonal path more probable. where (cid:12) is Hadamard product and L align is ﬁnal loss for alignments.”
WavThruVec: Latent speech representation as intermediate features for neural speech synthesis (2022, methodology): “We follow the training schedule of [24], to add the binarization term and hard alignments to the loss function.”