research
∙
09/06/2023
Matcha-TTS: A fast TTS architecture with conditional flow matching
We introduce Matcha-TTS, a new encoder-decoder architecture for speedy T...
share
research
∙
08/24/2023
The GENEA Challenge 2023: A large scale evaluation of gesture generation models in monadic and dyadic settings
This paper reports on the GENEA Challenge 2023, in which participating t...
research
∙
07/11/2023
On the Use of Self-Supervised Speech Representations in Spontaneous Speech Synthesis
Self-supervised learning (SSL) speech representations learned from large...
research
∙
06/15/2023
Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesis
With read-aloud speech synthesis achieving high naturalness scores, ther...
research
∙
03/15/2023
Evaluating gesture-generation in a large-scale open challenge: The GENEA Challenge 2022
This paper reports on the second GENEA Challenge to benchmark data-drive...
research
∙
03/13/2023
A processing framework to access large quantities of whispered speech found in ASMR
Whispering is a ubiquitous mode of communication that humans use daily. ...
research
∙
03/05/2023
A Comparative Study of Self-Supervised Speech Representations in Read and Spontaneous TTS
Recent work has explored using self-supervised learning (SSL) speech rep...
research
∙
01/24/2023
Context-specific kernel-based hidden Markov model for time series analysis
Traditional hidden Markov models have been a useful tool to understand a...
research
∙
01/13/2023
A Comprehensive Review of Data-Driven Co-Speech Gesture Generation
Gestures that accompany speech are an essential part of natural and effi...
research
∙
11/24/2022
Prosody-controllable spontaneous TTS with neural HMMs
Spontaneous speech has many affective and pragmatic functions that are i...
research
∙
11/17/2022
Listen, denoise, action! Audio-driven motion synthesis with diffusion models
Diffusion models have experienced a surge of interest as highly expressi...
research
∙
11/13/2022
Autovocoder: Fast Waveform Generation from a Learned Speech Representation using Differentiable Digital Signal Processing
Most state-of-the-art Text-to-Speech systems use the mel-spectrogram as ...
research
∙
11/13/2022
OverFlow: Putting flows on top of neural transducers for better TTS
Neural HMMs are a type of neural transducer recently proposed for sequen...
research
∙
09/22/2022
Predicting pairwise preferences between TTS audio stimuli using parallel ratings data and anti-symmetric twin neural networks
Automatically predicting the outcome of subjective listening tests is a ...
research
∙
08/22/2022
The GENEA Challenge 2022: A large evaluation of data-driven co-speech gesture generation
This paper reports on the second GENEA Challenge to benchmark data-drive...
research
∙
02/22/2022
Wavebender GAN: An architecture for phonetically meaningful speech manipulation
Deep learning has revolutionised synthetic speech quality. However, it h...
research
∙
08/30/2021
Neural HMMs are all you need (for high-quality attention-free TTS)
Neural sequence-to-sequence TTS has achieved significantly better output...
research
∙
08/25/2021
Integrated Speech and Gesture Synthesis
Text-to-speech and co-speech gesture synthesis have until now been treat...
research
∙
08/12/2021
Multimodal analysis of the predictability of hand-gesture properties
Embodied conversational agents benefit from being able to accompany thei...
research
∙
07/01/2021
Normalizing Flow based Hidden Markov Models for Classification of Speech Phones with Explainability
In pursuit of explainability, we develop generative models for sequentia...
research
∙
06/28/2021
Speech2Properties2Gestures: Gesture-Property Prediction as a Tool for Generating Representational Gestures from Speech
We propose a new framework for gesture generation, aiming to allow data-...
research
∙
06/25/2021
Transflower: probabilistic autoregressive dance generation with multimodal attention
Dance requires skillful composition of complex movements that follow rhy...
research
∙
06/03/2021
The Case for Translation-Invariant Self-Attention in Transformer-Based Language Models
Mechanisms for encoding positional information are central for transform...
research
∙
02/23/2021
A large, crowdsourced evaluation of gesture generation systems on common data: The GENEA Challenge 2020
Co-speech gestures, gestures that accompany speech, play an important ro...
research
∙
02/15/2021
Robust Classification using Hidden Markov Models and Mixtures of Normalizing Flows
We test the robustness of a maximum-likelihood (ML) based classifier whe...
research
∙
01/28/2021
HEMVIP: Human Evaluation of Multiple Videos in Parallel
In many research areas, for example motion and gesture generation, objec...
research
∙
01/14/2021
Generating coherent spontaneous speech and gesture from text
Embodied human communication encompasses both verbal (speech) and non-ve...
research
∙
12/10/2020
Full-Glow: Fully conditional Glow for more realistic image generation
Autonomous agents, such as driverless cars, require large amounts of lab...
research
∙
07/16/2020
Moving fast and slow: Analysis of representations and post-processing in speech-driven automatic gesture generation
This paper presents a novel framework for speech-driven gesture producti...
research
∙
06/11/2020
Robust model training and generalisation with Studentising flows
Normalising flows are tractable probabilistic models that leverage the p...
research
∙
06/11/2020
Let's face it: Probabilistic multi-modal interlocutor-aware generation of facial gestures in dyadic settings
To enable more natural face-to-face interactions, conversational agents ...
research
∙
01/25/2020
Gesticulator: A framework for semantically-aware speech-driven gesture generation
During speech, people spontaneously gesticulate, which plays a key role ...
research
∙
11/10/2019
Transformation of low-quality device-recorded speech to high-quality speech using improved SEGAN model
Nowadays vast amounts of speech data are recorded from low-quality recor...
research
∙
05/16/2019
MoGlow: Probabilistic and controllable motion synthesis using normalising flows
Data-driven modelling and synthesis of motion data is an active research...
research
∙
03/08/2019
Analyzing Input and Output Representations for Speech-Driven Gesture Generation
This paper presents a novel framework for automatic speech-driven gestur...
research
∙
07/30/2018
Deep Encoder-Decoder Models for Unsupervised Learning of Controllable Speech Synthesis
Generating versatile and appropriate synthetic speech requires control o...
research
∙
07/30/2018
Kernel Density Estimation-Based Markov Models with Hidden State
We consider Markov models of stochastic processes where the next-step co...
research
∙
07/28/2018
Analysing Shortcomings of Statistical Parametric Speech Synthesis
Output from statistical parametric speech synthesis (SPSS) remains notic...
research
∙
12/27/2017
Consensus-based Sequence Training for Video Captioning
Captioning models are typically trained using the cross-entropy loss. Ho...
research
∙
08/22/2016