Search

Abstract In the era of advanced text-to-speech (TTS) systems capable of generating high-fidelity, human-like speech by referring a reference speech, voice cloning (VC), or zero-shot TTS (ZS-TTS), stands out as an important subtask. A primary challenge in VC is maintaining speech quality and speaker similarity with limited reference data for a specific speaker. However, existing VC systems often rely on naive combinations of embedded speaker vectors for speaker control, which compromises the capture of speaking style, voice print, and semantic accuracy. To overcome this, we introduce the Two-branch Speaker Control Module (TSCM), a novel and highly adaptable voice cloning module designed to precisely processing speaker or style control for a target speaker. Our method uses an advanced fusion of local-level features from a Gated Convolutional Network (GCN) and utterance-level features from a gated recurrent unit (GRU) to enhance speaker control. We demonstrate the effectiveness of TSCM by integrating it into advanced TTS systems like FastSpeech 2 and VITS architectures, significantly optimizing their performance. Experimental results show that TSCM enables accurate voice cloning for a target speaker with minimal data through both zero-shot or few-shot fine-tuning of pretrained TTS models. Furthermore, our TSCM-based VITS (TSCM-VITS) showcases superior performance in zero-shot scenarios compared to existing state-of-the-art VC systems, even with basic dataset configurations. Our method’s superiority is validated through comprehensive subjective and objective evaluations. A demonstration of our system is available at https://great-research.github.io/tsct-tts-demo/ , providing practical insights into its application and effectiveness.

High-entropy shape-memory alloys (HESMAs) exhibit unique properties, including high yield strength, a wide temperature range of phase transformation, and excellent thermal cycling stability, among others. Hence, they have broad prospects for research and application. Currently, various new high-entropy shape-memory alloys have been developed based on TiNi, Fe-based, Ti-based, and NiMn-based alloys. This article focuses on summarizing and analyzing the research status of various types of high-entropy shape-memory alloys, including their microstructure characteristics, martensitic phase transformation, and functional properties. The advantages and disadvantages of high-entropy shape-memory alloys compared to traditional shape-memory alloys are briefly discussed. Finally, based on the analysis of existing problems, future research prospects are proposed, hoping to provide assistance for the development and application of high-entropy shape-memory alloys in the future.