Search Results for author:
Found 5 papers, 0 papers with code
Enhancing the Stability of LLM-based Speech Generation Systems through Self-Supervised Representations
Using speaker-disentangled codes to train LLMs for text-to-speech (TTS) allows the LLM to generate the content and the style of the speech only from the text, similarly to humans, while the speaker identity is provided by the decoder of the VC model.
SCRAPS: Speech Contrastive Representations of Acoustic and Phonetic Spaces
We train a CLIP-based model with the aim to learn shared representations of phonetic and acoustic spaces.
GlowVC: Mel-spectrogram space disentangling model for language-independent text-free voice conversion
We evaluate our models in terms of intelligibility, speaker similarity and naturalness for intra- and cross-lingual conversion in seen and unseen languages.
Improving multi-speaker TTS prosody variance with a residual encoder and normalizing flows
This paper proposes a new neural text-to-speech model that approaches the disentanglement problem by conditioning a Tacotron2-like architecture on flow-normalized speaker embeddings, and by substituting the reference encoder with a new learned latent distribution responsible for modeling the intra-sentence variability due to the prosody.
Detection of Lexical Stress Errors in Non-Native (L2) English with Data Augmentation and Attention
This paper describes two novel complementary techniques that improve the detection of lexical stress errors in non-native (L2) English speech: attention-based feature extraction and data augmentation based on Neural Text-To-Speech (TTS).
