Voice Imitating Text-to-Speech Neural Networks

By Younggun Lee, Taesu Kim, Soo-Young Lee. 2018

11 citations recorded by the source corpus.

We propose a neural text-to-speech (TTS) model that can imitate a new speaker's voice using only a small amount of speech sample. We demonstrate voice imitation using only a 6-seconds long speech sample without any other information such as transcripts. Our model also enables voice imitation instantly without additional training of the model. We implemented the voice imitating TTS model by combining a speaker embedder network with a state-of-the-art TTS model, Tacotron. The speaker embedder network takes a new speaker's speech sample and returns a speaker embedding. The speaker embedding with a target sentence are fed to Tacotron, and speech is generated with the new speaker's voice. We show that the speaker embeddings extracted by the speaker embedder network can represent the latent structure in different voices. The generated speech samples from our model have comparable voice quality to the ones from existing multi-speaker TTS models.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Khalid Mahmood Malik
2. Ali Javed
3. Momina Masood
4. Hafiz Malik
5. M. M. Tanzim Nawaz
6. Aun Irtaza

Citations in the corpus

• Deepfakes generation and detection: state-of-the-art, open challenges, countermeasures, and way forward (2021, methodology): “These methods include Neural vocoders [57-62], GAN[63-64], autoencoder [65], autoregressive models [52, 53, 187], and other emerging techniques [188-192] have promoted the rapid development of the speech synthesis industry.”