Mohammad Khan | Boston University (original) (raw)

Related Authors

viet anh tran

Lorenzo Lastilla

Siriwan Sirikaew

Mike Lewis

建宇 林

建宇 林

National Chiao Tung University

Uploads

Papers by Mohammad Khan

Research paper thumbnail of Unsupervised Cross-Domain Speech-to-Speech Conversion with Time-Frequency Consistency

ArXiv, 2020

In recent years generative adversarial network (GAN) based models have been successfully applied ... more 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...

Research paper thumbnail of Unsupervised Cross-Domain Speech-to-Speech Conversion with Time-Frequency Consistency

ArXiv, 2020

In recent years generative adversarial network (GAN) based models have been successfully applied ... more 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...

Log In