Picture for Jonas Rohnke

Jonas Rohnke

Analysis and Utilization of Entrainment on Acoustic and Emotion Features in User-agent Dialogue

Add code
Dec 07, 2022
Viaarxiv icon

Discrete acoustic space for an efficient sampling in neural text-to-speech

Add code
Oct 24, 2021
Figure 1 for Discrete acoustic space for an efficient sampling in neural text-to-speech
Figure 2 for Discrete acoustic space for an efficient sampling in neural text-to-speech
Figure 3 for Discrete acoustic space for an efficient sampling in neural text-to-speech
Figure 4 for Discrete acoustic space for an efficient sampling in neural text-to-speech
Viaarxiv icon

Dynamic Prosody Generation for Speech Synthesis using Linguistics-Driven Acoustic Embedding Selection

Add code
Dec 02, 2019
Figure 1 for Dynamic Prosody Generation for Speech Synthesis using Linguistics-Driven Acoustic Embedding Selection
Figure 2 for Dynamic Prosody Generation for Speech Synthesis using Linguistics-Driven Acoustic Embedding Selection
Figure 3 for Dynamic Prosody Generation for Speech Synthesis using Linguistics-Driven Acoustic Embedding Selection
Figure 4 for Dynamic Prosody Generation for Speech Synthesis using Linguistics-Driven Acoustic Embedding Selection
Viaarxiv icon

Fine-grained robust prosody transfer for single-speaker neural text-to-speech

Add code
Jul 04, 2019
Figure 1 for Fine-grained robust prosody transfer for single-speaker neural text-to-speech
Figure 2 for Fine-grained robust prosody transfer for single-speaker neural text-to-speech
Figure 3 for Fine-grained robust prosody transfer for single-speaker neural text-to-speech
Figure 4 for Fine-grained robust prosody transfer for single-speaker neural text-to-speech
Viaarxiv icon