seginr
SegINR: Segment-wise Implicit Neural Representation for Sequence Alignment in Neural Text-to-Speech
Kim, Minchan, Jeong, Myeonghun, Lee, Joun Yeop, Kim, Nam Soo
It leverages an optimal text encoder to extract embeddings, transforming each into a segment of frame-level features using a conditional implicit neural representation (INR). This method, named segment-wise INR (SegINR), models temporal dynamics within each segment and autonomously defines segment boundaries, reducing computational costs. We integrate SegINR into a two-stage TTS framework, using it for semantic token prediction. Our experiments in zero-shot adaptive TTS scenarios demonstrate that SegINR outperforms conventional methods in speech quality with computational efficiency.
2410.0469
Country:
- Asia > South Korea > Seoul > Seoul (0.05)
- North America > United States > California > San Diego County > San Diego (0.04)
- North America > Canada > Quebec > Montreal (0.04)
- Europe > Italy > Calabria > Catanzaro Province > Catanzaro (0.04)
Technology:
- Information Technology > Artificial Intelligence > Vision (1.00)
- Information Technology > Artificial Intelligence > Natural Language (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (0.94)
- Information Technology > Artificial Intelligence > Speech > Speech Synthesis (0.67)