Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Generative Models for Improved Naturalness, Intelligibility, and Voicing of Whispered Speech (2212.01775v2)

Published 4 Dec 2022 in cs.SD and eess.AS

Abstract: This work adapts two recent architectures of generative models and evaluates their effectiveness for the conversion of whispered speech to normal speech. We incorporate the normal target speech into the training criterion of vector-quantized variational autoencoders (VQ-VAEs) and MelGANs, thereby conditioning the systems to recover voiced speech from whispered inputs. Objective and subjective quality measures indicate that both VQ-VAEs and MelGANs can be modified to perform the conversion task. We find that the proposed approaches significantly improve the Mel cepstral distortion (MCD) metric by at least 25% relative to a DiscoGAN baseline. Subjective listening tests suggest that the MelGAN-based system significantly improves naturalness, intelligibility, and voicing compared to the whispered input speech. A novel evaluation measure based on differences between latent speech representations also indicates that our MelGAN-based approach yields improvements relative to the baseline.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Dominik Wagner (29 papers)
  2. Sebastian P. Bayerl (22 papers)
  3. Hector A. Cordourier Maruri (1 paper)
  4. Tobias Bocklet (30 papers)
Citations (5)

Summary

We haven't generated a summary for this paper yet.