Generating Multilingual Gender-Ambiguous Text-to-Speech Voices
This addresses the need for inclusive voice interfaces by providing a systematic method to create gender-ambiguous voices, though it is incremental as it builds on existing multi-speaker TTS frameworks.
The paper tackled generating novel gender-ambiguous text-to-speech voices in a multilingual setting, achieving voices perceived as more gender-ambiguous than a baseline across all languages with robust gender perception across listener demographics.
The gender of any voice user interface is a key element of its perceived identity. Recently, there has been increasing interest in interfaces where the gender is ambiguous rather than clearly identifying as female or male. This work addresses the task of generating novel gender-ambiguous TTS voices in a multi-speaker, multilingual setting. This is accomplished by efficiently sampling from a latent speaker embedding space using a proposed gender-aware method. Extensive objective and subjective evaluations clearly indicate that this method is able to efficiently generate a range of novel, diverse voices that are consistent and perceived as more gender-ambiguous than a baseline voice across all the languages examined. Interestingly, the gender perception is found to be robust across two demographic factors of the listeners: native language and gender. To our knowledge, this is the first systematic and validated approach that can reliably generate a variety of gender-ambiguous voices.