2606.09048v1 Jun 08, 2026 eess.AS

BareWave: Waveform-Native Flow-Matching Text-to-Speech

Neng H. Yu
Neng H. Yu
Citations: 2,242
h-index: 22
Xiangang Li
Xiangang Li
Citations: 61
h-index: 4
Qian Chen
Qian Chen
Citations: 698
h-index: 12
Wen Wang
Wen Wang
Citations: 895
h-index: 11
Weiming Zhang
Weiming Zhang
Citations: 44
h-index: 4
Kejiang Chen
Kejiang Chen
Citations: 969
h-index: 15
Wei Fan
Wei Fan
Citations: 5
h-index: 1
Chaohong Tan
Chaohong Tan
Citations: 131
h-index: 5

Removing intermediate representations and separately trained decoding stages has become an important direction in generative modeling. In text-to-speech, however, high-quality systems are still commonly built through an intermediate acoustic representation before waveform synthesis. In this work, we present BareWave, a fully waveform-native framework for direct text-to-wave generation in flow-matching TTS. We consider this setting to raise three training challenges: raw-waveform modeling lacks a strong pretrained representational scaffold, different stages of training benefit from different noise schedules, and data-space perceptual objectives do not automatically share the temporal structure of the velocity-space flow objective. As a result, direct waveform training is hard to optimize efficiently, hard to push toward a strong final operating point with a fixed recipe, and hard to integrate effective perceptual refinement. Guided by this view, we develop a direct text-to-wave training framework that combines training-time representation alignment, staged noise scheduling, and velocity-aware perceptual alignment (VAPA), while preserving a single waveform-native inference path without pretrained components at test time. Experiments on zero-shot voice cloning show that strong intelligibility, speaker similarity, and naturalness can be achieved under a fully waveform-native inference path, supporting waveform-native flow-matching TTS as a practical direction. Project page with audio demos is available at https://barewave.github.io/.

0 Citations
0 Influential
11 Altmetric
55.0 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!