pith. sign in

arxiv: 2005.07810 · v2 · pith:WKMMVYIMnew · submitted 2020-05-15 · 📡 eess.AS · cs.LG· cs.SD

Unsupervised Cross-Domain Speech-to-Speech Conversion with Time-Frequency Consistency

classification 📡 eess.AS cs.LGcs.SD
keywords spectrogramconsistencyconversionmagnitudespeech-to-speechadversarialapproachgenerated
0
0 comments X
read the original abstract

In recent years generative adversarial network (GAN) based models have been successfully applied for unsupervised speech-to-speech conversion.The rich compact harmonic view of the magnitude spectrogram is considered a suitable choice for training these models with audio data. To reconstruct the speech signal first a magnitude spectrogram is generated by the neural network, which is then utilized by methods like the Griffin-Lim algorithm to reconstruct a phase spectrogram. This procedure bears the problem that the generated magnitude spectrogram may not be consistent, which is required for finding a phase such that the full spectrogram has a natural-sounding speech waveform. In this work, we approach this problem by proposing a condition encouraging spectrogram consistency during the adversarial training procedure. We demonstrate our approach on the task of translating the voice of a male speaker to that of a female speaker, and vice versa. Our experimental results on the Librispeech corpus show that the model trained with the TF consistency provides a perceptually better quality of speech-to-speech conversion.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.