Santiago Pascual

66 papers A* 2A 5Misc 12Journal 31Unranked 16

Year	Rank	Type	Title / Venue / Authors
2025	Misc	`conf`	Joint Semantic Knowledge Distillation and Masked Acoustic Modeling for Full-band Speech Restoration With Improved Intelligibility. ICASSP Xiaoyu Liu, Xu Li, Joan Serrà, Santiago Pascual
2025	Misc	`conf`	Sequential Contrastive Audio-Visual Learning. ICASSP Ioannis Tsiamas, Santiago Pascual, Chunghsin Yeh, Joan Serrà
2025	J	`jnl`	Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play. CoRR Jiatong Shi, Jionghao Han, Yichen Lu, Santiago Pascual, Pengfei Wu, Chenye Cui, Shinji Watanabe, Chao Weng, Cong Zhou
2024	Misc	`conf`	GASS: Generalizing Audio Source Separation with Large-Scale Data. ICASSP Jordi Pons, Xiaoyu Liu, Santiago Pascual, Joan Serrà
2024	J	`jnl`	Joint Semantic Knowledge Distillation and Masked Acoustic Modeling for Full-band Speech Restoration with Improved Intelligibility. CoRR Xiaoyu Liu, Xu Li, Joan Serrà, Santiago Pascual
2024	—	`conf`	Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity. ECCV (87) Santiago Pascual, Chunghsin Yeh, Ioannis Tsiamas, Joan Serrà
2024	J	`jnl`	Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity. CoRR Santiago Pascual, Chunghsin Yeh, Ioannis Tsiamas, Joan Serrà
2024	J	`jnl`	Sequential Contrastive Audio-Visual Learning. CoRR Ioannis Tsiamas, Santiago Pascual, Chunghsin Yeh, Joan Serrà
2024	A*	`conf`	V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models. AAAI Heng Wang, Jianbo Ma, Santiago Pascual, Richard Cartwright, Weidong Cai
2023	Misc	`conf`	Adversarial Permutation Invariant Training for Universal Sound Separation. ICASSP Emilian Postolache, Jordi Pons, Santiago Pascual, Joan Serrà
2023	—	`conf`	CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models. WASPAA Hao-Wen Dong, Xiaoyu Liu, Jordi Pons, Gautam Bhattacharya, Santiago Pascual, Joan Serrà, Taylor Berg-Kirkpatrick, Julian J. McAuley
2023	J	`jnl`	CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models. CoRR Hao-Wen Dong, Xiaoyu Liu, Jordi Pons, Gautam Bhattacharya, Santiago Pascual, Joan Serrà, Taylor Berg-Kirkpatrick, Julian J. McAuley
2023	Misc	`conf`	Full-Band General Audio Synthesis with Score-Based Diffusion. ICASSP Santiago Pascual, Gautam Bhattacharya, Chunghsin Yeh, Jordi Pons, Joan Serrà
2023	J	`jnl`	GASS: Generalizing Audio Source Separation with Large-scale Data. CoRR Jordi Pons, Xiaoyu Liu, Santiago Pascual, Joan Serrà
2023	—	`conf`	Mono-to-Stereo Through Parametric Stereo Generation. ISMIR Joan Serrà, Davide Scaini, Santiago Pascual, Daniel Arteaga, Jordi Pons, Jeroen Breebaart, Giulio Cengarle
2023	J	`jnl`	Mono-to-stereo through parametric stereo generation. CoRR Joan Serrà, Davide Scaini, Santiago Pascual, Daniel Arteaga, Jordi Pons, Jeroen Breebaart, Giulio Cengarle
2023	—	`conf`	Upsampling Layers for Music Source Separation. EUSIPCO Jordi Pons, Joan Serrà, Santiago Pascual, Giulio Cengarle, Daniel Arteaga, Davide Scaini
2023	J	`jnl`	V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models. CoRR Heng Wang, Jianbo Ma, Santiago Pascual, Richard Cartwright, Weidong Cai
2022	J	`jnl`	Adversarial Permutation Invariant Training for Universal Sound Separation. CoRR Emilian Postolache, Jordi Pons, Santiago Pascual, Joan Serrà
2022	J	`jnl`	Full-band General Audio Synthesis with Score-based Diffusion. CoRR Santiago Pascual, Gautam Bhattacharya, Chunghsin Yeh, Jordi Pons, Joan Serrà
2022	Misc	`conf`	On Loss Functions and Evaluation Metrics for Music Source Separation. ICASSP Enric Gusó, Jordi Pons, Santiago Pascual, Joan Serrà
2022	J	`jnl`	On loss functions and evaluation metrics for music source separation. CoRR Enric Gusó, Jordi Pons, Santiago Pascual, Joan Serrà
2022	J	`jnl`	Universal Speech Enhancement with Score-based Diffusion. CoRR Joan Serrà, Santiago Pascual, Jordi Pons, Recep Oguz Araz, Davide Scaini
2021	—	`conf`	Adversarial Auto-Encoding for Packet Loss Concealment. WASPAA Santiago Pascual, Joan Serrà, Jordi Pons
2021	J	`jnl`	Adversarial Auto-Encoding for Packet Loss Concealment. CoRR Santiago Pascual, Joan Serrà, Jordi Pons
2021	Misc	`conf`	Automatic Multitrack Mixing With A Differentiable Mixing Console Of Neural Audio Effects. ICASSP Christian J. Steinmetz, Jordi Pons, Santiago Pascual, Joan Serrà
2021	J	`jnl`	On tuning consistent annealed sampling for denoising score matching. CoRR Joan Serrà, Santiago Pascual, Jordi Pons
2021	Misc	`conf`	SESQA: Semi-Supervised Learning for Speech Quality Assessment. ICASSP Joan Serrà, Jordi Pons, Santiago Pascual
2021	Misc	`conf`	Upsampling Artifacts in Neural Audio Synthesis. ICASSP Jordi Pons, Santiago Pascual, Giulio Cengarle, Joan Serrà
2021	J	`jnl`	Upsampling layers for music source separation. CoRR Jordi Pons, Joan Serrà, Santiago Pascual, Giulio Cengarle, Daniel Arteaga, Davide Scaini
2020	J	`jnl`	Automatic multitrack mixing with a differentiable mixing console of neural audio effects. CoRR Christian J. Steinmetz, Jordi Pons, Santiago Pascual, Joan Serrà
2020	A	`conf`	CATOTRON - A Neural Text-to-Speech System in Catalan. INTERSPEECH Baybars Külebi, Alp Öktem, Alex Peiró Lilja, Santiago Pascual, Mireia Farrús
2020	Misc	`conf`	Multi-Task Self-Supervised Learning for Robust Speech Recognition. ICASSP Mirco Ravanelli, Jianyuan Zhong, Santiago Pascual, Pawel Swietojanski, João Monteiro, Jan Trmal, Yoshua Bengio
2020	J	`jnl`	Multi-task self-supervised learning for Robust Speech Recognition. CoRR Mirco Ravanelli, Jianyuan Zhong, Santiago Pascual, Pawel Swietojanski, João Monteiro, Jan Trmal, Yoshua Bengio
2020	J	`jnl`	SESQA: semi-supervised learning for speech quality assessment. CoRR Joan Serrà, Jordi Pons, Santiago Pascual
2020	—	`conf`	Sample drop detection for asynchronous devices distributed in space. EUSIPCO Tina Raissi, Santiago Pascual, Maurizio Omologo
2020	J	`jnl`	Upsampling artifacts in neural audio synthesis. CoRR Jordi Pons, Santiago Pascual, Giulio Cengarle, Joan Serrà
2019	A*	`conf`	Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion. NeurIPS Joan Serrà, Santiago Pascual, Carlos Segura
2019	J	`jnl`	Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion. CoRR Joan Serrà, Santiago Pascual, Carlos Segura
2019	A	`conf`	Learning Problem-Agnostic Speech Representations from Multiple Self-Supervised Tasks. INTERSPEECH Santiago Pascual, Mirco Ravanelli, Joan Serrà, Antonio Bonafonte, Yoshua Bengio
2019	J	`jnl`	Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks. CoRR Santiago Pascual, Mirco Ravanelli, Joan Serrà, Antonio Bonafonte, Yoshua Bengio
2019	—	`conf`	Problem-Agnostic Speech Embeddings for Multi-Speaker Text-to-Speech with SampleRNN. SSW David Álvarez, Santiago Pascual, Antonio Bonafonte
2019	J	`jnl`	Problem-Agnostic Speech Embeddings for Multi-Speaker Text-to-Speech with SampleRNN. CoRR David Álvarez, Santiago Pascual, Antonio Bonafonte
2019	J	`jnl`	Sample Drop Detection for Distant-speech Recognition with Asynchronous Devices Distributed in Space. CoRR Tina Raissi, Santiago Pascual, Maurizio Omologo
2019	J	`jnl`	Time-domain speech enhancement using generative adversarial networks. Speech Commun. Santiago Pascual, Joan Serrà, Antonio Bonafonte
2019	A	`conf`	Towards Generalized Speech Enhancement with Generative Adversarial Networks. INTERSPEECH Santiago Pascual, Joan Serrà, Antonio Bonafonte
2019	J	`jnl`	Towards Generalized Speech Enhancement with Generative Adversarial Networks. CoRR Santiago Pascual, Joan Serrà, Antonio Bonafonte
2019	—	`conf`	WAV2PIX: Speech-conditioned Face Generation using Generative Adversarial Networks. CVPR Workshops Amanda Cardoso Duarte, Francisco Roldan, Miquel Tubau, Janna Escur, Santiago Pascual, Amaia Salvador, Eva Mohedano, Kevin McGuinness, Jordi Torres, Xavier Giró-i-Nieto
2019	Misc	`conf`	Wav2Pix: Speech-conditioned Face Generation Using Generative Adversarial Networks. ICASSP Amanda Cardoso Duarte, Francisco Roldan, Miquel Tubau, Janna Escur, Santiago Pascual, Amaia Salvador, Eva Mohedano, Kevin McGuinness, Jordi Torres, Xavier Giró-i-Nieto
2019	J	`jnl`	Wav2Pix: Speech-conditioned Face Generation using Generative Adversarial Networks. CoRR Amanda Cardoso Duarte, Francisco Roldan, Miquel Tubau, Janna Escur, Santiago Pascual, Amaia Salvador, Eva Mohedano, Kevin McGuinness, Jordi Torres, Xavier Giró-i-Nieto
2018	Misc	`conf`	Language and Noise Transfer in Speech Enhancement Generative Adversarial Network. ICASSP Santiago Pascual, Maruchan Park, Joan Serrà, Antonio Bonafonte, Kang-Hun Ahn
2018	—	`conf`	Multi-Speaker Neural Vocoder. IberSPEECH Oriol Barbany, Antonio Bonafonte, Santiago Pascual
2018	—	`conf`	Self-Attention Linguistic-Acoustic Decoder. IberSPEECH Santiago Pascual, Antonio Bonafonte, Joan Serrà
2018	J	`jnl`	Self-Attention Linguistic-Acoustic Decoder. CoRR Santiago Pascual, Antonio Bonafonte, Joan Serrà
2018	A	`conf`	Spanish Statistical Parametric Speech Synthesis Using a Neural Vocoder. INTERSPEECH Antonio Bonafonte, Santiago Pascual, Georgina Dorca
2018	—	`conf`	Towards a Universal Neural Network Encoder for Time Series. CCIA Joan Serrà, Santiago Pascual, Alexandros Karatzoglou
2018	J	`jnl`	Towards a universal neural network encoder for time series. CoRR Joan Serrà, Santiago Pascual, Alexandros Karatzoglou
2018	—	`conf`	Whispered-to-voiced Alaryngeal Speech Conversion with Generative Adversarial Networks. IberSPEECH Santiago Pascual, Antonio Bonafonte, Joan Serrà, José Andrés González López
2018	J	`jnl`	Whispered-to-voiced Alaryngeal Speech Conversion with Generative Adversarial Networks. CoRR Santiago Pascual, Antonio Bonafonte, Joan Serrà, José A. González
2017	J	`jnl`	Language and Noise Transfer in Speech Enhancement Generative Adversarial Network. CoRR Santiago Pascual, Maruchan Park, Joan Serrà, Antonio Bonafonte, Kang-Hun Ahn
2017	A	`conf`	SEGAN: Speech Enhancement Generative Adversarial Network. INTERSPEECH Santiago Pascual, Antonio Bonafonte, Joan Serrà
2017	J	`jnl`	SEGAN: Speech Enhancement Generative Adversarial Network. CoRR Santiago Pascual, Antonio Bonafonte, Joan Serrà
2016	—	`conf`	Acoustic feature prediction from semantic features for expressive speech using deep neural networks. EUSIPCO Igor Jauk, Antonio Bonafonte, Santiago Pascual
2016	—	`conf`	Multi-output RNN-LSTM for multiple speaker speech synthesis and adaptation. EUSIPCO Santiago Pascual, Antonio Bonafonte
2016	—	`conf`	Multi-output RNN-LSTM for multiple speaker speech synthesis with α-interpolation model. SSW Santiago Pascual, Antonio Bonafonte
2016	—	`conf`	Prosodic Break Prediction with RNNs. IberSPEECH Santiago Pascual, Antonio Bonafonte