Whispered-to-voiced Alaryngeal Speech Conversion With Generative Adversarial Networks

Abstract

Most methods of voice restoration for patients suffering from aphonia either produce whispered or monotone speech. Apart from intelligibility, this type of speech lacks expressiveness and naturalness due to the absence of pitch (whispered speech) or artificial generation of it (monotone speech). Existing techniques to restore prosodic information typically combine a vocoder, which parameterises the speech signal, with machine learning techniques that predict prosodic information. In contrast, this paper describes an end-to-end neural approach for estimating a fully-voiced speech waveform from whispered alaryngeal speech. By adapting our previous work in speech enhancement with generative adversarial networks, we develop a speaker-dependent model to perform whispered-to-voiced speech conversion. Preliminary qualitative results show effectiveness in re-generating voiced speech, with the creation of realistic pitch contours.

Stats

• citations17
• S2 citations—
• github stars0
• HF likes0
• heat score9.41
• arxiv keypascual2018whispered

Related papers

• Attention-guided Generative Adversarial Network For Whisper To Normal Speech Conversion (2021)5.84
• Vocoder-free Non-parallel Conversion Of Whispered Speech With Masked Cycle-consistent Generative Adversarial Networks (2023)0.00
• Generative Models For Improved Naturalness, Intelligibility, And Voicing Of Whispered Speech (2022)6.34
• Voice Impersonation Using Generative Adversarial Networks (2018)13.23
• Generative Adversarial Network Based Voice Conversion: Techniques, Challenges, And Recent Advancements (2025)0.00
• Video-driven Speech Reconstruction Using Generative Adversarial Networks (2019)11.39
• An Adaptive Learning Based Generative Adversarial Network For One-to-one Voice Conversion (2021)10.61
• Whispervc: Decoupled Cross-domain Alignment And Speech Generation For Low-resource Whisper-to-normal Conversion (2025)0.00