SegINR: Segment-wise Implicit Neural Representation for Sequence Alignment in Neural Text-to-Speech
Abstract
We present SegINR, a novel approach to neural Text-to-Speech (TTS) that addresses sequence alignment without relying on an auxiliary duration predictor and complex autoregressive (AR) or non-autoregressive (NAR) frame-level sequence modeling. SegINR simplifies the process by converting text sequences directly into frame-level features. 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.
Keywords
Cite
@article{arxiv.2410.04690,
title = {SegINR: Segment-wise Implicit Neural Representation for Sequence Alignment in Neural Text-to-Speech},
author = {Minchan Kim and Myeonghun Jeong and Joun Yeop Lee and Nam Soo Kim},
journal= {arXiv preprint arXiv:2410.04690},
year = {2024}
}
Comments
This work has been submitted to the IEEE for possible publication