Feb 10, 2021 · The proposed approach has the goal to overcome these limitations trying to obtain a system which is able to model a multi-speaker acoustic space.

A personalized voice cloning system that utilizes deep learning models for Text-to-speech (TTS) synthesis and audio generation

Nov 30, 2022 · The author's goal was to create a voice cloning system that could generate natural speech for a variety of target speakers while using minimal data.

Feb 10, 2021 · We demonstrate that the proposed model is able to transfer the knowledge of speaker variability learned by the discriminatively-trained speaker ...

Using a transfer learning technique from a speaker-discriminative encoder model based on utterance embeddings rather than speaker embeddings, the synthesizer ...

From a speaker verification challenge to text-to-speech synthesis with multi-speaker capability, the current study used a transfer learning technique. In a zero ...

In addition, it makes use of a novel transfer learning approach. Along with this, we explore several neural architectures for the speaker encoder model and use ...

Aug 20, 2024 · The speech Synthesis module acts as the text-to-speech translator, i.e., when it gets the translated text. This module processes translated text ...

May 30, 2024 · This study outlines an unconventional method of text-to-speech with voice cloning, focusing on creating a custom model instead of using pre-existing ones.

We present a multispeaker, multilingual text-to-speech (TTS) synthesis model based on Tacotron that is able to produce high quality speech in multiple languages ...