English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In recent years, large-scale pre-trained speech language models (SLMs) havedemonstrated remarkable advancements in various generative speech modelingapplications, such as text-to-speech synthesis, voice conversion, and speechenhancement. These applications typically involve mapping text or speech inputsto pre-trained SLM representations, from which target speech is decoded. Thispaper introduces a new approach, SLMGAN, to leverage SLM representations fordiscriminative tasks within the generative adversarial network (GAN) framework,specifically for voice conversion. Building upon StarGANv2-VC, we add our novelSLM-based WavLM discriminators on top of the mel-based discriminators alongwith our newly designed SLM feature matching loss function, resulting in anunsupervised zero-shot voice conversion system that does not require textlabels during training. Subjective evaluation results show that SLMGANoutperforms existing state-of-the-art zero-shot voice conversion models interms of naturalness and achieves comparable similarity, highlighting thepotential of SLM-based discriminators for related applications.

SLMGAN: Exploiting Speech Language Model Representations for Unsupervised Zero-Shot Voice Conversion in GANs