Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Gustav Eje Henter

Gustav Eje Henter

Evaluating gesture-generation in a large-scale open challenge: The GENEA Challenge 2022

Mar 15, 2023
Taras Kucherenko, Pieter Wolfert, Youngwoo Yoon, Carla Viegas, Teodor Nikolov, Mihail Tsakov, Gustav Eje Henter

Figure 1 for Evaluating gesture-generation in a large-scale open challenge: The GENEA Challenge 2022

Figure 2 for Evaluating gesture-generation in a large-scale open challenge: The GENEA Challenge 2022

Figure 3 for Evaluating gesture-generation in a large-scale open challenge: The GENEA Challenge 2022

Figure 4 for Evaluating gesture-generation in a large-scale open challenge: The GENEA Challenge 2022

* The first three authors made equal contributions and share joint first authorship. arXiv admin note: substantial text overlap with arXiv:2208.10441

Access Paper or Ask Questions

A processing framework to access large quantities of whispered speech found in ASMR

Mar 13, 2023
Pablo Perez Zarazaga, Gustav Eje Henter, Zofia Malisz

Figure 1 for A processing framework to access large quantities of whispered speech found in ASMR

Figure 2 for A processing framework to access large quantities of whispered speech found in ASMR

Figure 3 for A processing framework to access large quantities of whispered speech found in ASMR

Figure 4 for A processing framework to access large quantities of whispered speech found in ASMR

* Accepted at ICASSP 2023, 5 pages, 2 figures, 2 tables

Access Paper or Ask Questions

A Comparative Study of Self-Supervised Speech Representations in Read and Spontaneous TTS

Mar 05, 2023
Siyang Wang, Gustav Eje Henter, Joakim Gustafson, Éva Székely

Figure 1 for A Comparative Study of Self-Supervised Speech Representations in Read and Spontaneous TTS

Figure 2 for A Comparative Study of Self-Supervised Speech Representations in Read and Spontaneous TTS

Figure 3 for A Comparative Study of Self-Supervised Speech Representations in Read and Spontaneous TTS

Figure 4 for A Comparative Study of Self-Supervised Speech Representations in Read and Spontaneous TTS

* 5 pages, 2 figures. In submission

Access Paper or Ask Questions

Context-specific kernel-based hidden Markov model for time series analysis

Jan 24, 2023
Carlos Puerto-Santana, Concha Bielza, Pedro Larrañaga, Gustav Eje Henter

Figure 1 for Context-specific kernel-based hidden Markov model for time series analysis

Figure 2 for Context-specific kernel-based hidden Markov model for time series analysis

Figure 3 for Context-specific kernel-based hidden Markov model for time series analysis

Figure 4 for Context-specific kernel-based hidden Markov model for time series analysis

* Keywords: Hidden Markov models, Kernel density estimation, Bayesian networks, Adaptive models, Time series

Access Paper or Ask Questions

Prosody-controllable spontaneous TTS with neural HMMs

Nov 24, 2022
Harm Lameris, Shivam Mehta, Gustav Eje Henter, Joakim Gustafson, Éva Székely

Figure 1 for Prosody-controllable spontaneous TTS with neural HMMs

Figure 2 for Prosody-controllable spontaneous TTS with neural HMMs

Figure 3 for Prosody-controllable spontaneous TTS with neural HMMs

Figure 4 for Prosody-controllable spontaneous TTS with neural HMMs

* 5 pages, 3 figures, Submitted to ICASSP 2023

Access Paper or Ask Questions

Listen, denoise, action! Audio-driven motion synthesis with diffusion models

Nov 17, 2022
Simon Alexanderson, Rajmund Nagy, Jonas Beskow, Gustav Eje Henter

Figure 1 for Listen, denoise, action! Audio-driven motion synthesis with diffusion models

Figure 2 for Listen, denoise, action! Audio-driven motion synthesis with diffusion models

Figure 3 for Listen, denoise, action! Audio-driven motion synthesis with diffusion models

Figure 4 for Listen, denoise, action! Audio-driven motion synthesis with diffusion models

* 15 pages, 6 figures

Access Paper or Ask Questions

Autovocoder: Fast Waveform Generation from a Learned Speech Representation using Differentiable Digital Signal Processing

Nov 13, 2022
Jacob J Webber, Cassia Valentini-Botinhao, Evelyn Williams, Gustav Eje Henter, Simon King

Figure 1 for Autovocoder: Fast Waveform Generation from a Learned Speech Representation using Differentiable Digital Signal Processing

Figure 2 for Autovocoder: Fast Waveform Generation from a Learned Speech Representation using Differentiable Digital Signal Processing

Figure 3 for Autovocoder: Fast Waveform Generation from a Learned Speech Representation using Differentiable Digital Signal Processing

Figure 4 for Autovocoder: Fast Waveform Generation from a Learned Speech Representation using Differentiable Digital Signal Processing

* Submitted to the 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023)

Access Paper or Ask Questions

OverFlow: Putting flows on top of neural transducers for better TTS

Nov 13, 2022
Shivam Mehta, Ambika Kirkland, Harm Lameris, Jonas Beskow, Éva Székely, Gustav Eje Henter

Figure 1 for OverFlow: Putting flows on top of neural transducers for better TTS

Figure 2 for OverFlow: Putting flows on top of neural transducers for better TTS

Figure 3 for OverFlow: Putting flows on top of neural transducers for better TTS

Figure 4 for OverFlow: Putting flows on top of neural transducers for better TTS

* 5 pages, 2 figures, submitted to ICASSP 2023

Access Paper or Ask Questions