REVIEW 6 cited by
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems. In this work, we present a parallel end-to-end TTS method that generates more natural sounding audio than current two-stage models. Our method adopts variational inference augmented with normalizing flows and an adversarial training process, which improves the expressive power of generative modeling. We also propose a stochastic duration predictor to synthesize speech with diverse rhythms from input text. With the uncertainty modeling over latent variables and the stochastic duration predictor, our method expresses the natural one-to-many relationship in which a text input can be spoken in multiple ways with different pitches and rhythms. A subjective human evaluation (mean opinion score, or MOS) on the LJ Speech, a single speaker dataset, shows that our method outperforms the best publicly available TTS systems and achieves a MOS comparable to ground truth.
Forward citations
Cited by 6 Pith papers
-
Conversations with Andrea: Visitors' Opinions on Android Robots in a Museum
A fully autonomous android robot conversed with museum visitors for six days, was rated positively, and visitor requests point to exhibit information, multilingual support, and lower latency as the next steps.
-
Towards Digital Preservation of Efik: TTS for a Low-Resource African Language
First end-to-end Efik TTS baseline: a 3-hour single-speaker corpus and four fine-tuned models, with MMS-TTS best at MOS 3.80±0.63 but residual tonal errors.
-
EmoNews: A Spoken Dialogue System for Expressive News Conversations
An emotional spoken dialogue system that uses a sentiment analyzer to pick an emotion tag and PromptTTS to synthesize matching speech outperforms a neutral baseline on perceived emotional appropriateness, but not sign...
-
KLASSify to Verify: Audio-Visual Deepfake Detection Using SSL-based Audio and Handcrafted Visual Features
A challenge entry combining Wav2Vec-AASIST audio scores with lightweight handcrafted-feature video scores via calibration and maxout reports 92.78% AUC on AV-Deepfake1M++ testA.
-
Marco-Voice Technical Report
Marco-Voice is a TTS system combining voice cloning and emotional speech generation via speaker-emotion disentanglement, contrastive learning, and a new Mandarin emotional dataset, with claimed quality gains over Cosy...
-
Technical report: Impact of Duration Prediction on Speaker-specific TTS for Indian Languages
In a five-language zero-shot TTS study, no single duration prediction strategy dominates: speaker-prompted durations help some languages, infilling durations help others, and results vary by metric.
Discussion (0). Sign in to comment.