# Attention-based speech feature transfer between speakers

## TL;DR

This paper introduces a method to transfer speech characteristics from one speaker to another using attention models in speech synthesis.

## Contribution

The novelty lies in using attention weights to transfer speaker-specific features like pitch and intensity between different speakers.

## Key findings

- Replacing attention weights from the source speaker with those from the target speaker successfully transfers speech style.
- The model's effectiveness was validated using five evaluation metrics and real-world examples.
- The approach allows generating target speaker speech with the style of a source speaker.

## Abstract

In this study, we propose a simple yet effective method for incorporating the source speaker's characteristics in the target speaker's speech. This allows our model to generate the speech of the target speaker with the style of the source speaker. To achieve this, we focus on the attention model within the speech synthesis model, which learns various speaker features such as spectrogram, pitch, intensity, formant, pulse, and voice breaks. The model is trained separately using datasets specific to the source and target speakers. Subsequently, we replace the attention weights learned from the source speaker's dataset with the attention weights from the target speaker's model. Finally, by providing new input texts to the target model, we generate the speech of the target speaker with the styles of the source speaker. We validate the effectiveness of our model through similarity analysis utilizing five evaluation metrics and showcase real-world examples.