Jun 29, 2022 · This paper presents a novel cross-speaker emotion transfer system, named iEmoTTS. The system is composed of an emotion encoder, a prosody predictor, and a ...

Unlike many other studies which focus on disentangling speaker and style factors of speech, the. iEmoTTS is designed to achieve cross-speaker emotion transfer.

May 4, 2023 · Unlike many other studies which focus on disentangling speaker and style factors of speech, the iEmoTTS is designed to achieve cross-speaker ...

iEmoTTS: Toward robust cross-speaker emotion transfer and control for speech synthesis based on disentanglement between prosody and timbre. G Zhang, Y Qin, W ...

The system is composed of an emotion encoder, a prosody predictor, and a timbre encoder. The emotion encoder extracts the identity of emotion type and the ...

It is shown that iEmoTTS can produce speech with designated emotion types and controllable emotion intensity and is able to transfer emotional information ...

Experimental results show that the proposed cross-speaker emotion transfer method outperforms the multi-reference based baseline in terms of timbre ...

iEmoTTS: Toward Robust Cross-Speaker Emotion Transfer and Control for Speech Synthesis Based on Disentanglement Between Prosody and Timbre. Article. Jan 2023.

iEmoTTS: Toward Robust Cross-Speaker Emotion Transfer and Control for Speech Synthesis based on Disentanglement between Prosody and Timbre · no code ...

Unlike many other studies which focus on disentangling speaker and style factors of speech, the iEmoTTS is designed to achieve cross-speaker emotion transfer ...