arXiv Machine Learning
Learnable Classifier-Free Guidance Null Embeddings for Enhanced Controllable Speech Synthesis
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 2
Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis
arXiv:2607. 00363v1 Announce Type: cross Abstract: Flow Matching (FM) has emerged as a powerful paradigm for speech generation but remains constrained by high inference latency and timbre leakage.
arXiv AI
Aug 11
CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latents
arXiv:2608. 08638v1 Announce Type: cross Abstract: Zero-shot text-to-speech (TTS) now supports interactive assistants, personalized media, and accessibility tools.
arXiv AI
Jun 19
ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis
arXiv:2603. 04219v2 Announce Type: replace-cross Abstract: We investigate the use of zero-shot text-to-speech (ZS-TTS) as a data augmentation source for low-resource personalized speech synthesis.
arXiv AI
Jun 9
GenTSE: Enhancing Target Speaker Extraction via a Coarse-to-Fine Generative Language Model
arXiv:2512. 20978v2 Announce Type: replace-cross Abstract: Language Model (LM)-based generative modeling has emerged as a promising direction for TSE, offering potential for improved generalization and high-fidelity speech.
arXiv Machine Learning
5d ago
A Comprehensive Study of Content Representations for Speech Synthesis
The paper investigates how different speech content representations—such as SSL features, supervised tokens, posteriorgrams, and neural audio codecs—perform when used to train a generative model that produces audio conditioned only on each representation. By evaluating the generated audio on content, speaker identity, and prosody, the study identifies two regimes: some representations almost fully reconstruct the original audio, while others effectively separate speaker identity. The findings reveal that disentanglement of speaker identity depends on both the training objective and the representation’s information capacity, rather than supervision alone.
arXiv Machine Learning
Aug 31
Rethinking Speaker Embeddings for Speech Generation: Sub-Center Modeling for Capturing Intra-Speaker Diversity
arXiv:2407.04291v4 Announce Type: replace-cross Abstract: Modeling speech variation is key to natural, expressive generation. Speaker embeddings are commonly used to condition personalized speech sys...