ARCHI-TTS: A flow-matching-based Text-to-Speech Model with Self-supervised Semantic Aligner and Accelerated Inference
This addresses efficiency and alignment issues in TTS for applications requiring high-quality, fast speech synthesis, representing a strong incremental improvement.
The paper tackled the challenges of text-speech alignment and high computational cost in diffusion-based TTS by proposing ARCHI-TTS with a semantic aligner and accelerated inference, achieving WERs as low as 1.42% and outperforming SOTA systems.
Although diffusion-based, non-autoregressive text-to-speech (TTS) systems have demonstrated impressive zero-shot synthesis capabilities, their efficacy is still hindered by two key challenges: the difficulty of text-speech alignment modeling and the high computational overhead of the iterative denoising process. To address these limitations, we propose ARCHI-TTS that features a dedicated semantic aligner to ensure robust temporal and semantic consistency between text and audio. To overcome high computational inference costs, ARCHI-TTS employs an efficient inference strategy that reuses encoder features across denoising steps, drastically accelerating synthesis without performance degradation. An auxiliary CTC loss applied to the condition encoder further enhances the semantic understanding. Experimental results demonstrate that ARCHI-TTS achieves a WER of 1.98% on LibriSpeech-PC test-clean, and 1.47%/1.42% on SeedTTS test-en/test-zh with a high inference efficiency, consistently outperforming recent state-of-the-art TTS systems.