Voice Conversion using Convolutional Neural Networks
This addresses the challenge of speaker identification and voice manipulation for audio processing applications, but it appears incremental as it builds on existing neural network methods.
The paper tackled the problem of voice conversion by transforming both pitch and timbre using neural networks, with preliminary results showing encouraging outcomes for converting voices between speakers.
The human auditory system is able to distinguish the vocal source of thousands of speakers, yet not much is known about what features the auditory system uses to do this. Fourier Transforms are capable of capturing the pitch and harmonic structure of the speaker but this alone proves insufficient at identifying speakers uniquely. The remaining structure, often referred to as timbre, is critical to identifying speakers but we understood little about it. In this paper we use recent advances in neural networks in order to manipulate the voice of one speaker into another by transforming not only the pitch of the speaker, but the timbre. We review generative models built with neural networks as well as architectures for creating neural networks that learn analogies. Our preliminary results converting voices from one speaker to another are encouraging.