Gustav Eje Henter

142 papers A* 2A 22B 14Misc 15Journal 73Unranked 15

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	The Voice Behind the Words: Quantifying Intersectional Bias in SpeechLLMs. CoRR Shree Harsha Bokkahalli Satish, Christoph Minixhofer, Maria Teleki, James Caverlee, Ondrej Klejch, Peter Bell, Gustav Eje Henter, Éva Székely
2026	J	`jnl`	VoXtream2: Full-stream TTS with dynamic speaking rate control. CoRR Nikita Torgashov, Gustav Eje Henter, Gabriel Skantze
2025	A	`conf`	A Non-Adversarial Approach to Idempotent Generative Modelling. ECAI Mohammed Al-Jaff, Giovanni Luca Marchetti, Michael C. Welle, Jens Lundell, Mats G. Gustafsson, Gustav Eje Henter, Hossein Azizpour, Danica Kragic
2025	J	`jnl`	A Non-Adversarial Approach to Idempotent Generative Modelling. CoRR Mohammed Al-Jaff, Giovanni Luca Marchetti, Michael C. Welle, Jens Lundell, Mats G. Gustafsson, Gustav Eje Henter, Hossein Azizpour, Danica Kragic
2025	J	`jnl`	Do Bias Benchmarks Generalise? Evidence from Voice-based Evaluation of Gender Bias in SpeechLLMs. CoRR Shree Harsha Bokkahalli Satish, Gustav Eje Henter, Éva Székely
2025	B	`conf`	EmojiVoice: Towards long-term controllable expressivity in robot speech. RO-MAN Paige Tuttösí, Shivam Mehta, Zachary Syvenky, Bermet Burkanova, Gustav Eje Henter, Angelica Lim
2025	J	`jnl`	EmojiVoice: Towards long-term controllable expressivity in robot speech. CoRR Paige Tuttösí, Shivam Mehta, Zachary Syvenky, Bermet Burkanova, Gustav Eje Henter, Angelica Lim
2025	A*	`conf`	GENEA Workshop 2025: The 6th Workshop on Generation and Evaluation of Non-verbal Behaviour for Embodied Agents. ACM Multimedia Taras Kucherenko, Alice Delbosc, Rajmund Nagy, Laura B. Hensel, Youngwoo Yoon, Oya Çeliktutan, Gustav Eje Henter
2025	J	`jnl`	Gelina: Unified Speech and Gesture Synthesis via Interleaved Token Prediction. CoRR Teo Guichoux, Théodor Lemerle, Shivam Mehta, Jonas Beskow, Gustav Eje Henter, Laure Soulier, Catherine Pelachaud, Nicolas Obin
2025	J	`jnl`	Gesture Generation (Still) Needs Improved Human Evaluation Practices: Insights from a Community-Driven State-of-the-Art Benchmark. CoRR Rajmund Nagy, Hendric Voss, Thanh Hoang-Minh, Mihail Tsakov, Teodor Nikolov, Zeyi Zhang, Tenglong Ao, Sicheng Yang, Shaoli Huang, Yongkang Cheng, Muhammad Hamza Mughal, Rishabh Dabral, Kiran Chhatre, Christian Theobalt, Libin Liu, Stefan Kopp, Rachel McDonnell, Michael Neff, Taras Kucherenko, Youngwoo Yoon, Gustav Eje Henter
2025	A	`conf`	Hear Me Out: Interactive evaluation and bias discovery platform for speech-to-speech conversational AI. INTERSPEECH Shree Harsha Bokkahalli Satish, Gustav Eje Henter, Éva Székely
2025	A	`conf`	SawtArabi: A Benchmark Corpus for Arabic TTS. Standard, Dialectal and Code-Switching. INTERSPEECH Vasista Sai Lodagala, Lamya Alkanhal, Daniel Izham, Shivam Mehta, Shammur Absar Chowdhury, Aqeelah Makki, Hamdy S. Hussein, Gustav Eje Henter, Ahmed Ali
2025	J	`jnl`	Speak Your Mind: The Speech Continuation Task as a Probe of Voice-Based Model Bias. CoRR Shree Harsha Bokkahalli Satish, Harm Lameris, Olivier Perrotin, Gustav Eje Henter, Éva Székely
2025	A*	`conf`	Take a Look, it's in a Book, a Reading Robot. HRI Paige Tuttösí, Shivam Mehta, Zachary Syvenky, Bermet Burkanova, Mohammed Hfsafsti, Yue Wang, H. Henny Yeung, Gustav Eje Henter, Jean-Julien Aucouturier, Angelica Lim
2025	J	`jnl`	VoXtream: Full-Stream Text-to-Speech with Extremely Low Latency. CoRR Nikita Torgashov, Gustav Eje Henter, Gabriel Skantze
2025	—	`conf`	When Voice Matters: Evidence of Gender Disparity in Positional Bias of SpeechLLMs. SPECOM (1) Shree Harsha Bokkahalli Satish, Gustav Eje Henter, Éva Székely
2025	J	`jnl`	When Voice Matters: Evidence of Gender Disparity in Positional Bias of SpeechLLMs. CoRR Shree Harsha Bokkahalli Satish, Gustav Eje Henter, Éva Székely
2024	J	`jnl`	CARL-GT: Evaluating Causal Reasoning Capabilities of Large Language Models. CoRR Ruibo Tu, Hedvig Kjellström, Gustav Eje Henter, Cheng Zhang
2024	J	`jnl`	Causality for Tabular Data Synthesis: A High-Order Structure Causal Benchmark Framework. CoRR Ruibo Tu, Zineb Senane, Lele Cao, Cheng Zhang, Hedvig Kjellström, Gustav Eje Henter
2024	J	`jnl`	Evaluating Gesture Generation in a Large-scale Open Challenge: The GENEA Challenge 2022. ACM Trans. Graph. Taras Kucherenko, Pieter Wolfert, Youngwoo Yoon, Carla Viegas, Teodor Nikolov, Mihail Tsakov, Gustav Eje Henter
2024	J	`jnl`	Exploring Internal Numeracy in Language Models: A Case Study on ALBERT. CoRR Ulme Wennberg, Gustav Eje Henter
2024	—	`conf`	Fake it to make it: Using synthetic data to remedy the data shortage in joint multi-modal speech-and-gesture synthesis. CVPR Workshops Shivam Mehta, Anna Deichler, Jim O'Regan, Birger Moëll, Jonas Beskow, Gustav Eje Henter, Simon Alexanderson
2024	J	`jnl`	Fake it to make it: Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesis. CoRR Shivam Mehta, Anna Deichler, Jim O'Regan, Birger Moëll, Jonas Beskow, Gustav Eje Henter, Simon Alexanderson
2024	B	`conf`	GENEA Workshop 2024: The 5th Workshop on Generation and Evaluation of Non-verbal Behaviour for Embodied Agents. ICMI Youngwoo Yoon, Taras Kucherenko, Alice Delbosc, Rajmund Nagy, Teodor Nikolov, Gustav Eje Henter
2024	J	`jnl`	HiFi-Glot: Neural Formant Synthesis with Differentiable Resonant Filters. CoRR Lauri Juvela, Pablo Pérez Zarazaga, Gustav Eje Henter, Zofia Malisz
2024	Misc	`conf`	Matcha-TTS: A Fast TTS Architecture with Conditional Flow Matching. ICASSP Shivam Mehta, Ruibo Tu, Jonas Beskow, Éva Székely, Gustav Eje Henter
2024	A	`conf`	Should you use a probabilistic duration model in TTS? Probably! Especially for spontaneous speech. INTERSPEECH Shivam Mehta, Harm Lameris, Rajiv Punmiya, Jonas Beskow, Éva Székely, Gustav Eje Henter
2024	J	`jnl`	Should you use a probabilistic duration model in TTS? Probably! Especially for spontaneous speech. CoRR Shivam Mehta, Harm Lameris, Rajiv Punmiya, Jonas Beskow, Éva Székely, Gustav Eje Henter
2024	J	`jnl`	Towards a GENEA Leaderboard - an Extended, Living Benchmark for Evaluating and Advancing Conversational Motion Synthesis. CoRR Rajmund Nagy, Hendric Voß, Youngwoo Yoon, Taras Kucherenko, Teodor Nikolov, Thanh Hoang-Minh, Rachel McDonnell, Stefan Kopp, Michael Neff, Gustav Eje Henter
2024	Misc	`conf`	Unified Speech and Gesture Synthesis Using Flow Matching. ICASSP Shivam Mehta, Ruibo Tu, Simon Alexanderson, Jonas Beskow, Éva Székely, Gustav Eje Henter
2024	J	`jnl`	Voice Conversion-based Privacy through Adversarial Information Hiding. CoRR Jacob J. Webber, Oliver Watts, Gustav Eje Henter, Jennifer Williams, Simon King
2023	—	`conf`	"Am I listening?", Evaluating the Quality of Generated Data-driven Listening Motion. ICMI Companion Pieter Wolfert, Gustav Eje Henter, Tony Belpaeme
2023	—	`conf`	A Comparative Study of Self-Supervised Speech Representations in Read and Spontaneous TTS. ICASSP Workshops Siyang Wang, Gustav Eje Henter, Joakim Gustafson, Éva Székely
2023	J	`jnl`	A Comparative Study of Self-Supervised Speech Representations in Read and Spontaneous TTS. CoRR Siyang Wang, Gustav Eje Henter, Joakim Gustafson, Éva Székely
2023	J	`jnl`	A Comprehensive Review of Data-Driven Co-Speech Gesture Generation. Comput. Graph. Forum Simbarashe Nyatsanga, Taras Kucherenko, Chaitanya Ahuja, Gustav Eje Henter, Michael Neff
2023	J	`jnl`	A Comprehensive Review of Data-Driven Co-Speech Gesture Generation. CoRR Simbarashe Nyatsanga, Taras Kucherenko, Chaitanya Ahuja, Gustav Eje Henter, Michael Neff
2023	Misc	`conf`	A Processing Framework to Access Large Quantities of Whispered Speech Found in ASMR. ICASSP Pablo Pérez Zarazaga, Gustav Eje Henter, Zofia Malisz
2023	J	`jnl`	A processing framework to access large quantities of whispered speech found in ASMR. CoRR Pablo Pérez Zarazaga, Gustav Eje Henter, Zofia Malisz
2023	Misc	`conf`	Autovocoder: Fast Waveform Generation from a Learned Speech Representation Using Differentiable Digital Signal Processing. ICASSP Jacob J. Webber, Cassia Valentini-Botinhao, Evelyn Williams, Gustav Eje Henter, Simon King
2023	J	`jnl`	Context-specific kernel-based hidden Markov model for time series analysis. CoRR Carlos Puerto-Santana, Concha Bielza, Pedro Larrañaga, Gustav Eje Henter
2023	—	`conf`	Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesis. SSW Shivam Mehta, Siyang Wang, Simon Alexanderson, Jonas Beskow, Éva Székely, Gustav Eje Henter
2023	J	`jnl`	Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesis. CoRR Shivam Mehta, Siyang Wang, Simon Alexanderson, Jonas Beskow, Éva Székely, Gustav Eje Henter
2023	J	`jnl`	Evaluating gesture-generation in a large-scale open challenge: The GENEA Challenge 2022. CoRR Taras Kucherenko, Pieter Wolfert, Youngwoo Yoon, Carla Viegas, Teodor Nikolov, Mihail Tsakov, Gustav Eje Henter
2023	B	`conf`	GENEA Workshop 2023: The 4th Workshop on Generation and Evaluation of Non-verbal Behaviour for Embodied Agents. ICMI Youngwoo Yoon, Taras Kucherenko, Jieyeon Woo, Pieter Wolfert, Rajmund Nagy, Gustav Eje Henter
2023	J	`jnl`	Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models. ACM Trans. Graph. Simon Alexanderson, Rajmund Nagy, Jonas Beskow, Gustav Eje Henter
2023	J	`jnl`	Matcha-TTS: A fast TTS architecture with conditional flow matching. CoRR Shivam Mehta, Ruibo Tu, Jonas Beskow, Éva Székely, Gustav Eje Henter
2023	—	`conf`	On the Use of Self-Supervised Speech Representations in Spontaneous Speech Synthesis. SSW Siyang Wang, Gustav Eje Henter, Joakim Gustafson, Éva Székely
2023	J	`jnl`	On the Use of Self-Supervised Speech Representations in Spontaneous Speech Synthesis. CoRR Siyang Wang, Gustav Eje Henter, Joakim Gustafson, Éva Székely
2023	A	`conf`	OverFlow: Putting flows on top of neural transducers for better TTS. INTERSPEECH Shivam Mehta, Ambika Kirkland, Harm Lameris, Jonas Beskow, Éva Székely, Gustav Eje Henter
2023	Misc	`conf`	Prosody-Controllable Spontaneous TTS with Neural HMMS. ICASSP Harm Lameris, Shivam Mehta, Gustav Eje Henter, Joakim Gustafson, Éva Székely
2023	A	`conf`	Speaker-independent neural formant synthesis. INTERSPEECH Pablo Pérez Zarazaga, Zofia Malisz, Gustav Eje Henter, Lauri Juvela
2023	—	`conf`	Stuck in the MOS pit: A critical analysis of MOS test methodology in TTS evaluation. SSW Ambika Kirkland, Shivam Mehta, Harm Lameris, Gustav Eje Henter, Éva Székely, Joakim Gustafson
2023	J	`jnl`	The GENEA Challenge 2023: A large scale evaluation of gesture generation models in monadic and dyadic settings. CoRR Taras Kucherenko, Rajmund Nagy, Youngwoo Yoon, Jieyeon Woo, Teodor Nikolov, Mihail Tsakov, Gustav Eje Henter
2023	B	`conf`	The GENEA Challenge 2023: A large-scale evaluation of gesture generation models in monadic and dyadic settings. ICMI Taras Kucherenko, Rajmund Nagy, Youngwoo Yoon, Jieyeon Woo, Teodor Nikolov, Mihail Tsakov, Gustav Eje Henter
2023	J	`jnl`	Unified speech and gesture synthesis using flow matching. CoRR Shivam Mehta, Ruibo Tu, Simon Alexanderson, Jonas Beskow, Éva Székely, Gustav Eje Henter
2022	J	`jnl`	Autovocoder: Fast Waveform Generation from a Learned Speech Representation using Differentiable Digital Signal Processing. CoRR Jacob J. Webber, Cassia Valentini-Botinhao, Evelyn Williams, Gustav Eje Henter, Simon King
2022	B	`conf`	GENEA Workshop 2022: The 3rd Workshop on Generation and Evaluation of Non-verbal Behaviour for Embodied Agents. ICMI Pieter Wolfert, Taras Kucherenko, Carla Viegas, Zerrin Yumak, Youngwoo Yoon, Gustav Eje Henter
2022	J	`jnl`	Kernel-based hidden Markov conditional densities. Comput. Stat. Data Anal. Jan G. De Gooijer, Gustav Eje Henter, Ao Yuan
2022	J	`jnl`	Listen, denoise, action! Audio-driven motion synthesis with diffusion models. CoRR Simon Alexanderson, Rajmund Nagy, Jonas Beskow, Gustav Eje Henter
2022	A	`conf`	Multimodal Analysis of the Predictability of Hand-gesture Properties. AAMAS Taras Kucherenko, Rajmund Nagy, Michael Neff, Hedvig Kjellström, Gustav Eje Henter
2022	Misc	`conf`	Neural HMMS Are All You Need (For High-Quality Attention-Free TTS). ICASSP Shivam Mehta, Éva Székely, Jonas Beskow, Gustav Eje Henter
2022	J	`jnl`	OverFlow: Putting flows on top of neural transducers for better TTS. CoRR Shivam Mehta, Ambika Kirkland, Harm Lameris, Jonas Beskow, Éva Székely, Gustav Eje Henter
2022	A	`conf`	Predicting pairwise preferences between TTS audio stimuli using parallel ratings data and anti-symmetric twin neural networks. INTERSPEECH Cassia Valentini-Botinhao, Manuel Sam Ribeiro, Oliver Watts, Korin Richmond, Gustav Eje Henter
2022	J	`jnl`	Predicting pairwise preferences between TTS audio stimuli using parallel ratings data and anti-symmetric twin neural networks. CoRR Cassia Valentini-Botinhao, Manuel Sam Ribeiro, Oliver Watts, Korin Richmond, Gustav Eje Henter
2022	J	`jnl`	Prosody-controllable spontaneous TTS with neural HMMs. CoRR Harm Lameris, Shivam Mehta, Gustav Eje Henter, Joakim Gustafson, Éva Székely
2022	A	`conf`	Speech Audio Corrector: using speech from non-target speakers for one-off correction of mispronunciations in grapheme-input text-to-speech. INTERSPEECH Jason Fong, Daniel Lyth, Gustav Eje Henter, Hao Tang, Simon King
2022	B	`conf`	The GENEA Challenge 2022: A large evaluation of data-driven co-speech gesture generation. ICMI Youngwoo Yoon, Pieter Wolfert, Taras Kucherenko, Carla Viegas, Teodor Nikolov, Mihail Tsakov, Gustav Eje Henter
2022	J	`jnl`	The GENEA Challenge 2022: A large evaluation of data-driven co-speech gesture generation. CoRR Youngwoo Yoon, Pieter Wolfert, Taras Kucherenko, Carla Viegas, Teodor Nikolov, Mihail Tsakov, Gustav Eje Henter
2022	Misc	`conf`	Wavebender GAN: An Architecture for Phonetically Meaningful Speech Manipulation. ICASSP Gustavo Teodoro Döhler Beck, Ulme Wennberg, Zofia Malisz, Gustav Eje Henter
2022	J	`jnl`	Wavebender GAN: An architecture for phonetically meaningful speech manipulation. CoRR Gustavo Teodoro Döhler Beck, Ulme Wennberg, Zofia Malisz, Gustav Eje Henter
2021	A	`conf`	A Large, Crowdsourced Evaluation of Gesture Generation Systems on Common Data: The GENEA Challenge 2020. IUI Taras Kucherenko, Patrik Jonell, Youngwoo Yoon, Pieter Wolfert, Gustav Eje Henter
2021	J	`jnl`	A large, crowdsourced evaluation of gesture generation systems on common data: The GENEA Challenge 2020. CoRR Taras Kucherenko, Patrik Jonell, Youngwoo Yoon, Pieter Wolfert, Gustav Eje Henter
2021	—	`conf`	Full-Glow: Fully Conditional Glow for More Realistic Image Generation. GCPR Moein Sorkhei, Gustav Eje Henter, Hedvig Kjellström
2021	B	`conf`	GENEA Workshop 2021: The 2nd Workshop on Generation and Evaluation of Non-verbal Behaviour for Embodied Agents. ICMI Taras Kucherenko, Patrik Jonell, Youngwoo Yoon, Pieter Wolfert, Zerrin Yumak, Gustav Eje Henter
2021	J	`jnl`	Generating coherent spontaneous speech and gesture from text. CoRR Simon Alexanderson, Éva Székely, Gustav Eje Henter, Taras Kucherenko, Jonas Beskow
2021	B	`conf`	HEMVIP: Human Evaluation of Multiple Videos in Parallel. ICMI Patrik Jonell, Youngwoo Yoon, Pieter Wolfert, Taras Kucherenko, Gustav Eje Henter
2021	J	`jnl`	HEMVIP: Human Evaluation of Multiple Videos in Parallel. CoRR Patrik Jonell, Youngwoo Yoon, Pieter Wolfert, Taras Kucherenko, Gustav Eje Henter
2021	B	`conf`	Integrated Speech and Gesture Synthesis. ICMI Siyang Wang, Simon Alexanderson, Joakim Gustafson, Jonas Beskow, Gustav Eje Henter, Éva Székely
2021	J	`jnl`	Integrated Speech and Gesture Synthesis. CoRR Siyang Wang, Simon Alexanderson, Joakim Gustafson, Jonas Beskow, Gustav Eje Henter, Éva Székely
2021	J	`jnl`	Moving Fast and Slow: Analysis of Representations and Post-Processing in Speech-Driven Automatic Gesture Generation. Int. J. Hum. Comput. Interact. Taras Kucherenko, Dai Hasegawa, Naoshi Kaneko, Gustav Eje Henter, Hedvig Kjellström
2021	J	`jnl`	Multimodal Capture of Patient Behaviour for Improved Detection of Early Dementia: Clinical Feasibility and Preliminary Results. Frontiers Comput. Sci. Patrik Jonell, Birger Moëll, Krister Håkansson, Gustav Eje Henter, Taras Kucherenko, Olga Mikheeva, Göran Hagman, Jasper Holleman, Miia Kivipelto, Hedvig Kjellström, Joakim Gustafson, Jonas Beskow
2021	J	`jnl`	Multimodal analysis of the predictability of hand-gesture properties. CoRR Taras Kucherenko, Rajmund Nagy, Michael Neff, Hedvig Kjellström, Gustav Eje Henter
2021	J	`jnl`	Neural HMMs are all you need (for high-quality attention-free TTS). CoRR Shivam Mehta, Éva Székely, Jonas Beskow, Gustav Eje Henter
2021	J	`jnl`	Normalizing Flow based Hidden Markov Models for Classification of Speech Phones with Explainability. CoRR Anubhab Ghosh, Antoine Honoré, Dong Liu, Gustav Eje Henter, Saikat Chatterjee
2021	J	`jnl`	Robust Classification using Hidden Markov Models and Mixtures of Normalizing Flows. CoRR Anubhab Ghosh, Antoine Honoré, Dong Liu, Gustav Eje Henter, Saikat Chatterjee
2021	B	`conf`	Speech2Properties2Gestures: Gesture-Property Prediction as a Tool for Generating Representational Gestures from Speech. IVA Taras Kucherenko, Rajmund Nagy, Patrik Jonell, Michael Neff, Hedvig Kjellström, Gustav Eje Henter
2021	J	`jnl`	Speech2Properties2Gestures: Gesture-Property Prediction as a Tool for Generating Representational Gestures from Speech. CoRR Taras Kucherenko, Rajmund Nagy, Patrik Jonell, Michael Neff, Hedvig Kjellström, Gustav Eje Henter
2021	—	`conf`	The Case for Translation-Invariant Self-Attention in Transformer-Based Language Models. ACL/IJCNLP (2) Ulme Wennberg, Gustav Eje Henter
2021	J	`jnl`	The Case for Translation-Invariant Self-Attention in Transformer-Based Language Models. CoRR Ulme Wennberg, Gustav Eje Henter
2021	J	`jnl`	Transflower: probabilistic autoregressive dance generation with multimodal attention. CoRR Guillermo Valle Pérez, Gustav Eje Henter, Jonas Beskow, Andre Holzapfel, Pierre-Yves Oudeyer, Simon Alexanderson
2021	J	`jnl`	Transflower: probabilistic autoregressive dance generation with multimodal attention. ACM Trans. Graph. Guillermo Valle Pérez, Gustav Eje Henter, Jonas Beskow, Andre Holzapfel, Pierre-Yves Oudeyer, Simon Alexanderson
2020	Misc	`conf`	Breathing and Speech Planning in Spontaneous Speech Synthesis. ICASSP Éva Székely, Gustav Eje Henter, Jonas Beskow, Joakim Gustafson
2020	J	`jnl`	Full-Glow: Fully conditional Glow for more realistic image generation. CoRR Moein Sorkhei, Gustav Eje Henter, Hedvig Kjellström
2020	B	`conf`	Generating coherent spontaneous speech and gesture from text. IVA Simon Alexanderson, Éva Székely, Gustav Eje Henter, Taras Kucherenko, Jonas Beskow
2020	B	`conf`	Gesticulator: A framework for semantically-aware speech-driven gesture generation. ICMI Taras Kucherenko, Patrik Jonell, Sanne van Waveren, Gustav Eje Henter, Simon Alexandersson, Iolanda Leite, Hedvig Kjellström
2020	J	`jnl`	Gesticulator: A framework for semantically-aware speech-driven gesture generation. CoRR Taras Kucherenko, Patrik Jonell, Sanne van Waveren, Gustav Eje Henter, Simon Alexanderson, Iolanda Leite, Hedvig Kjellström
2020	B	`conf`	Let's Face It: Probabilistic Multi-modal Interlocutor-aware Generation of Facial Gestures in Dyadic Settings. IVA Patrik Jonell, Taras Kucherenko, Gustav Eje Henter, Jonas Beskow
2020	J	`jnl`	Let's face it: Probabilistic multi-modal interlocutor-aware generation of facial gestures in dyadic settings. CoRR Patrik Jonell, Taras Kucherenko, Gustav Eje Henter, Jonas Beskow
2020	J	`jnl`	MoGlow: probabilistic and controllable motion synthesis using normalising flows. ACM Trans. Graph. Gustav Eje Henter, Simon Alexanderson, Jonas Beskow
2020	J	`jnl`	Moving fast and slow: Analysis of representations and post-processing in speech-driven automatic gesture generation. CoRR Taras Kucherenko, Dai Hasegawa, Naoshi Kaneko, Gustav Eje Henter, Hedvig Kjellström
2020	—	`conf`	Robust Classification Using Hidden Markov Models and Mixtures of Normalizing Flows. MLSP Anubhab Ghosh, Antoine Honoré, Dong Liu, Gustav Eje Henter, Saikat Chatterjee
2020	J	`jnl`	Robust model training and generalisation with Studentising flows. CoRR Simon Alexanderson, Gustav Eje Henter
2020	J	`jnl`	Style-Controllable Speech-Driven Gesture Synthesis Using Normalising Flows. Comput. Graph. Forum Simon Alexanderson, Gustav Eje Henter, Taras Kucherenko, Jonas Beskow
2019	B	`conf`	Analyzing Input and Output Representations for Speech-Driven Gesture Generation. IVA Taras Kucherenko, Dai Hasegawa, Gustav Eje Henter, Naoshi Kaneko, Hedvig Kjellström
2019	J	`jnl`	Analyzing Input and Output Representations for Speech-Driven Gesture Generation. CoRR Taras Kucherenko, Dai Hasegawa, Gustav Eje Henter, Naoshi Kaneko, Hedvig Kjellström
2019	Misc	`conf`	Casting to Corpus: Segmenting and Selecting Spontaneous Dialogue for Tts with a Cnn-lstm Speaker-dependent Breath Detector. ICASSP Éva Székely, Gustav Eje Henter, Joakim Gustafson
2019	—	`conf`	How to train your fillers: uh and um in spontaneous speech synthesis. SSW Éva Székely, Gustav Eje Henter, Jonas Beskow, Joakim Gustafson
2019	J	`jnl`	MoGlow: Probabilistic and controllable motion synthesis using normalising flows. CoRR Gustav Eje Henter, Simon Alexanderson, Jonas Beskow
2019	A	`conf`	Off the Cuff: Exploring Extemporaneous Speech Delivery with TTS. INTERSPEECH Éva Székely, Gustav Eje Henter, Jonas Beskow, Joakim Gustafson
2019	A	`conf`	On the Importance of Representations for Speech-Driven Gesture Generation. AAMAS Taras Kucherenko, Dai Hasegawa, Naoshi Kaneko, Gustav Eje Henter, Hedvig Kjellström
2019	—	`conf`	Speech Synthesis Evaluation - State-of-the-Art Assessment and Suggestion for a Novel Research Program. SSW Petra Wagner, Jonas Beskow, Simon Betz, Jens Edlund, Joakim Gustafson, Gustav Eje Henter, Sébastien Le Maguer, Zofia Malisz, Éva Székely, Christina Tånnander, Jana Voße
2019	A	`conf`	Spontaneous Conversational Speech Synthesis from Found Data. INTERSPEECH Éva Székely, Gustav Eje Henter, Jonas Beskow, Joakim Gustafson
2019	J	`jnl`	Transformation of low-quality device-recorded speech to high-quality speech using improved SEGAN model. CoRR Seyyed Saeed Sarfjoo, Xin Wang, Gustav Eje Henter, Jaime Lorenzo-Trueba, Shinji Takaki, Junichi Yamagishi
2019	—	`conf`	Where do the improvements come from in sequence-to-sequence neural TTS? SSW Oliver Watts, Gustav Eje Henter, Jason Fong, Cassia Valentini-Botinhao
2018	J	`jnl`	Analysing Shortcomings of Statistical Parametric Speech Synthesis. CoRR Gustav Eje Henter, Simon King, Thomas Merritt, Gilles Degottex
2018	Misc	`conf`	Cyborg Speech: Deep Multilingual Speech Synthesis for Generating Segmental Foreign Accent with Natural Prosody. ICASSP Gustav Eje Henter, Jaime Lorenzo-Trueba, Xin Wang, Mariko Kondo, Junichi Yamagishi
2018	J	`jnl`	Deep Encoder-Decoder Models for Unsupervised Learning of Controllable Speech Synthesis. CoRR Gustav Eje Henter, Xin Wang, Junichi Yamagishi
2018	J	`jnl`	Investigating different representations for modeling and controlling multiple emotions in DNN-based speech synthesis. Speech Commun. Jaime Lorenzo-Trueba, Gustav Eje Henter, Shinji Takaki, Junichi Yamagishi, Yosuke Morino, Yuta Ochiai
2018	J	`jnl`	Kernel Density Estimation-Based Markov Models with Hidden State. CoRR Gustav Eje Henter, Arne Leijon, W. Bastiaan Kleijn
2017	Misc	`conf`	Adapting and controlling DNN-based speech synthesis using input codes. ICASSP Hieu-Thi Luong, Shinji Takaki, Gustav Eje Henter, Junichi Yamagishi
2017	J	`jnl`	Consensus-based Sequence Training for Video Captioning. CoRR Sang Phan, Gustav Eje Henter, Yusuke Miyao, Shin'ichi Satoh
2017	A	`conf`	Misperceptions of the Emotional Content of Natural and Vocoded Speech in a Car. INTERSPEECH Jaime Lorenzo-Trueba, Cassia Valentini-Botinhao, Gustav Eje Henter, Junichi Yamagishi
2017	A	`conf`	Principles for Learning Controllable TTS from Annotated and Latent Variation. INTERSPEECH Gustav Eje Henter, Jaime Lorenzo-Trueba, Xin Wang, Junichi Yamagishi
2016	A	`conf`	A Hierarchical Predictor of Synthetic Speech Naturalness Using Neural Networks. INTERSPEECH Takenori Yoshimura, Gustav Eje Henter, Oliver Watts, Mirjam Wester, Junichi Yamagishi, Keiichi Tokuda
2016	A	`conf`	A Template-Based Approach for Speech Synthesis Intonation Generation Using LSTMs. INTERSPEECH Srikanth Ronanki, Gustav Eje Henter, Zhizheng Wu, Simon King
2016	J	`jnl`	Bayesian Analysis of Phoneme Confusion Matrices. IEEE ACM Trans. Audio Speech Lang. Process. Leijon Leijon, Gustav Eje Henter, Martin Dahlquist
2016	Misc	`conf`	From HMMS to DNNS: Where do the improvements come from? ICASSP Oliver Watts, Gustav Eje Henter, Thomas Merritt, Zhizheng Wu, Simon King
2016	J	`jnl`	Median-Based Generation of Synthetic Speech Durations using a Non-Parametric Approach. CoRR Srikanth Ronanki, Oliver Watts, Simon King, Gustav Eje Henter
2016	—	`conf`	Median-based generation of synthetic speech durations using a non-parametric approach. SLT Srikanth Ronanki, Oliver Watts, Simon King, Gustav Eje Henter
2016	J	`jnl`	Minimum Entropy Rate Simplification of Stochastic Processes. IEEE Trans. Pattern Anal. Mach. Intell. Gustav Eje Henter, W. Bastiaan Kleijn
2016	Misc	`conf`	Robust TTS duration modelling using DNNS. ICASSP Gustav Eje Henter, Srikanth Ronanki, Oliver Watts, Mirjam Wester, Zhizheng Wu, Simon King
2016	Misc	`conf`	Testing the consistency assumption: Pronunciation variant forced alignment in read and spontaneous speech synthesis. ICASSP Rasmus Dall, Sandrine Brognaux, Korin Richmond, Cassia Valentini-Botinhao, Gustav Eje Henter, Julia Hirschberg, Junichi Yamagishi, Simon King
2015	A	`conf`	Are we using enough listeners? no! - an empirically-supported critique of interspeech 2014 TTS evaluations. INTERSPEECH Mirjam Wester, Cassia Valentini-Botinhao, Gustav Eje Henter
2014	A	`conf`	A flexible front-end for HTS. INTERSPEECH Matthew P. Aylett, Rasmus Dall, Arnab Ghoshal, Gustav Eje Henter, Thomas Merritt
2014	A	`conf`	Measuring the perceptual effects of modelling assumptions in speech synthesis using stimuli constructed from repeated natural speech. INTERSPEECH Gustav Eje Henter, Thomas Merritt, Matt Shannon, Catherine Mayo, Simon King
2013	J	`jnl`	Maximizing Phoneme Recognition Accuracy for Enhanced Speech Intelligibility in Noise. IEEE Trans. Speech Audio Process. Petko Nikolov Petkov, Gustav Eje Henter, W. Bastiaan Kleijn
2013	J	`jnl`	Picking up the pieces: Causal states in noisy data, and how to recover them. Pattern Recognit. Lett. Gustav Eje Henter, W. Bastiaan Kleijn
2013	—	`—`	Probabilistic Sequence Models with Speech and Language Applications. Gustav Eje Henter
2012	A	`conf`	Enhancing Subjective Speech Intelligibility Using a Statistical Model of Speech. INTERSPEECH Petko Nikolov Petkov, W. Bastiaan Kleijn, Gustav Eje Henter
2012	Misc	`conf`	Gaussian process dynamical models for nonparametric speech representation and synthesis. ICASSP Gustav Eje Henter, Marcus R. Frean, W. Bastiaan Kleijn
2011	A	`conf`	Intermediate-State HMMs to Capture Continuously-Changing Signal Features. INTERSPEECH Gustav Eje Henter, W. Bastiaan Kleijn
2010	—	`conf`	Simplified probability models for generative tasks: A rate-distortion approach. EUSIPCO Gustav Eje Henter, W. Bastiaan Kleijn