Edresson Casanova

53 papers A* 2A 8B 3C 1Misc 2Journal 25Unranked 11

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Tagarela - A Portuguese speech dataset from podcasts. CoRR Frederico Santos de Oliveira, Lucas Rafael Stefanel Gris, Alef Iury Siqueira Ferreira, Augusto Seben da Rosa, Alexandre Costa Ferro Filho, Edresson Casanova, Christopher Dane Shulby, Rafael Teixeira Sousa, Diogo Fernandes Costa Silva, Anderson da Silva Soares, Arlindo Rodrigues Galvão Filho
2025	J	`jnl`	Align2Speak: Improving TTS for Low Resource Languages via ASR-Guided Online Preference Optimization. CoRR Shehzeen Hussain, Paarth Neekhara, Xuesong Yang, Edresson Casanova, Subhankar Ghosh, Roy Fejgin, Ryan Langman, Mikyas T. Desta, Leili Tavabi, Jason Li
2025	A	`conf`	Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model. INTERSPEECH Ke Hu, Ehsan Hosseini-Asl, Chen Chen, Edresson Casanova, Subhankar Ghosh, Piotr Zelasko, Zhehuai Chen, Jason Li, Jagadeesh Balam, Boris Ginsburg
2025	J	`jnl`	Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model. CoRR Ke Hu, Ehsan Hosseini-Asl, Chen Chen, Edresson Casanova, Subhankar Ghosh, Piotr Zelasko, Zhehuai Chen, Jason Li, Jagadeesh Balam, Boris Ginsburg
2025	J	`jnl`	Frame-Stacked Local Transformers For Efficient Multi-Codebook Speech Generation. CoRR Roy Fejgin, Paarth Neekhara, Xuesong Yang, Edresson Casanova, Ryan Langman Jaehyeon Kim, Subhankar Ghosh, Shehzeen Hussain, Jason Li
2025	Misc	`conf`	FreeSVC: Towards Zero-shot Multilingual Singing Voice Conversion. ICASSP Alef Iury Siqueira Ferreira, Lucas Rafael Stefanel Gris, Augusto Seben da Rosa, Frederico Santos de Oliveira, Edresson Casanova, Rafael Teixeira Sousa, Arnaldo Cândido Jr., Anderson da Silva Soares, Arlindo R. Galvão Filho
2025	J	`jnl`	FreeSVC: Towards Zero-shot Multilingual Singing Voice Conversion. CoRR Alef Iury Siqueira Ferreira, Lucas R. S. Gris, Augusto Seben da Rosa, Frederico Santos de Oliveira, Edresson Casanova, Rafael Teixeira Sousa, Arnaldo Cândido Júnior, Anderson da Silva Soares, Arlindo R. Galvão Filho
2025	A	`conf`	HiFiTTS-2: A Large-Scale High Bandwidth Speech Dataset. INTERSPEECH Ryan Langman, Xuesong Yang, Paarth Neekhara, Shehzeen Hussain, Edresson Casanova, Evelina Bakhturina, Jason Li
2025	A*	`conf`	Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance. EMNLP Shehzeen Samarah Hussain, Paarth Neekhara, Xuesong Yang, Edresson Casanova, Subhankar Ghosh, Roy Fejgin, Mikyas T. Desta, Rafael Valle, Jason Li
2025	J	`jnl`	Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance. CoRR Shehzeen Hussain, Paarth Neekhara, Xuesong Yang, Edresson Casanova, Subhankar Ghosh, Mikyas T. Desta, Roy Fejgin, Rafael Valle, Jason Li
2025	Misc	`conf`	Low Frame-rate Speech Codec: a Codec Designed for Fast High-quality Speech LLM Training and Inference. ICASSP Edresson Casanova, Ryan Langman, Paarth Neekhara, Shehzeen Hussain, Jason Li, Subhankar Ghosh, Ante Jukic, Sang-gil Lee
2025	B	`conf`	MuPe Life Stories Dataset: Spontaneous Speech in Brazilian Portuguese with a Case Study Evaluation on ASR Bias against Speakers Groups and Topic Modeling. COLING Sidney Evaldo Leal, Arnaldo Cândido Júnior, Ricardo M. Marcacini, Edresson Casanova, Odilon Gonçalves, Anderson da Silva Soares, Rodrigo Lima, Lucas Rafael Stefanel Gris, Sandra M. Aluísio
2025	A	`conf`	NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference. INTERSPEECH Edresson Casanova, Paarth Neekhara, Ryan Langman, Shehzeen Hussain, Subhankar Ghosh, Xuesong Yang, Ante Jukic, Jason Li, Boris Ginsburg
2025	J	`jnl`	NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference. CoRR Edresson Casanova, Paarth Neekhara, Ryan Langman, Shehzeen Hussain, Subhankar Ghosh, Xuesong Yang, Ante Jukic, Jason Li, Boris Ginsburg
2025	C	`conf`	Open Full-duplex Voice Agent with Speech-to-Speech Language Model. ASRU Edresson Casanova, Chen Chen, Kevin Hu, Ankita Pasad, Elena Rastorgueva, Seelan Lakshmi Narasimhan, Slyne Deng, Ehsan Hosseini-Asl, Piotr Zelasko, Valentin Mendelev, Subhankar Ghosh, Yifan Peng, Zhehuai Chen, Jason Li, Jagadeesh Balam, Vitaly Lavrukhin, Boris Ginsburg
2025	—	`conf`	The Impact of Prosodic Segmentation on Speech Synthesis of Spontaneous Speech. BRACIS (2) Julio Cesar Galdino, Sidney Evaldo Leal, Letícia Gabriella de Souza, Rodrigo Lima, Antonio Moreira, Arnaldo Cândido Jr., Miguel Oliveira Jr., Edresson Casanova, Sandra M. Aluísio
2025	J	`jnl`	The Impact of Prosodic Segmentation on Speech Synthesis of Spontaneous Speech. CoRR Julio Cesar Galdino, Sidney Evaldo Leal, Letícia Gabriella de Souza, Rodrigo de F. Lima, Antonio Nelson Fornari Mendes Moreira, Arnaldo Cândido Jr., Miguel Oliveira Jr., Edresson Casanova, Sandra M. Aluísio
2024	J	`jnl`	Low Frame-rate Speech Codec: a Codec Designed for Fast High-quality Speech LLM Training and Inference. CoRR Edresson Casanova, Ryan Langman, Paarth Neekhara, Shehzeen Hussain, Jason Li, Subhankar Ghosh, Ante Jukic, Sang-gil Lee
2024	B	`conf`	MLAAD: The Multi-Language Audio Anti-Spoofing Dataset. IJCNN Nicolas M. Müller, Piotr Kawa, Wei Herng Choong, Edresson Casanova, Eren Gölge, Thorsten Müller, Piotr Syga, Philip Sperl, Konstantin Böttinger
2024	J	`jnl`	MLAAD: The Multi-Language Audio Anti-Spoofing Dataset. CoRR Nicolas M. Müller, Piotr Kawa, Wei Herng Choong, Edresson Casanova, Eren Gölge, Thorsten Müller, Piotr Syga, Philip Sperl, Konstantin Böttinger
2024	—	`conf`	TTS applied to the generation of datasets for automatic speech recognition. PROPOR (1) Edresson Casanova, Sandra M. Aluísio, Moacir Antonelli Ponti
2024	A	`conf`	XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model. INTERSPEECH Edresson Casanova, Kelly Davis, Eren Gölge, Görkem Göknar, Iulian Gulea, Logan Hart, Aya Aljafari, Joshua Meyer, Reuben Morais, Samuel Olayemi, Julian Weber
2024	J	`jnl`	XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model. CoRR Edresson Casanova, Kelly Davis, Eren Gölge, Görkem Göknar, Iulian Gulea, Logan Hart, Aya Aljafari, Joshua Meyer, Reuben Morais, Samuel Olayemi, Julian Weber
2023	A	`conf`	ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion. INTERSPEECH Edresson Casanova, Christopher Shulby, Alexander Korolev, Arnaldo Cândido Júnior, Anderson da Silva Soares, Sandra M. Aluísio, Moacir Antonelli Ponti
2023	J	`jnl`	CML-TTS A Multilingual Dataset for Speech Synthesis in Low-Resource Languages. CoRR Frederico Santos de Oliveira, Edresson Casanova, Arnaldo Cândido Júnior, Anderson da Silva Soares, Arlindo R. Galvão Filho
2023	—	`conf`	CML-TTS: A Multilingual Dataset for Speech Synthesis in Low-Resource Languages. TSD Frederico Santos de Oliveira, Edresson Casanova, Arnaldo Cândido Júnior, Anderson da Silva Soares, Arlindo R. Galvão Filho
2023	J	`jnl`	CORAA ASR: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese. Lang. Resour. Evaluation Arnaldo Cândido Júnior, Edresson Casanova, Anderson da Silva Soares, Frederico Santos de Oliveira, Lucas Oliveira, Ricardo Corso Fernandes Junior, Daniel Peixoto Pinto da Silva, Fernando Gorgulho Fayet, Bruno Baldissera Carlotto, Lucas Rafael Stefanel Gris, Sandra Maria Aluísio
2023	J	`jnl`	Evaluating OpenAI's Whisper ASR for Punctuation Prediction and Topic Modeling of life histories of the Museum of the Person. CoRR Lucas Rafael Stefanel Gris, Ricardo M. Marcacini, Arnaldo Cândido Júnior, Edresson Casanova, Anderson da Silva Soares, Sandra Maria Aluísio
2023	—	`conf`	Evaluation of Speech Representations for MOS Prediction. TSD Frederico Santos de Oliveira, Edresson Casanova, Arnaldo Cândido Júnior, Lucas R. S. Gris, Anderson da Silva Soares, Arlindo R. Galvão Filho
2023	J	`jnl`	Evaluation of Speech Representations for MOS prediction. CoRR Frederico Santos de Oliveira, Edresson Casanova, Arnaldo Cândido Júnior, Lucas R. S. Gris, Anderson da Silva Soares, Arlindo R. Galvão Filho
2022	J	`jnl`	A single speaker is almost all you need for automatic speech recognition. CoRR Edresson Casanova, Christopher Shulby, Alexander Korolev, Arnaldo Cândido Júnior, Anderson da Silva Soares, Sandra M. Aluísio, Moacir Antonelli Ponti
2022	A	`conf`	BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus. INTERSPEECH Josh Meyer, David Ifeoluwa Adelani, Edresson Casanova, Alp Öktem, Daniel Whitenack, Julian Weber, Salomon Kabongo, Elizabeth Salesky, Iroro Orife, Colin Leong, Perez Ogayo, Chris Chinenye Emezue, Jonathan Mukiibi, Salomey Osei, Apelete Agbolo, Victor Akinode, Bernard Opoku, Samuel Olanrewaju, Jesujoba O. Alabi, Shamsuddeen Hassan Muhammad
2022	J	`jnl`	BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus. CoRR Josh Meyer, David Ifeoluwa Adelani, Edresson Casanova, Alp Öktem, Daniel Whitenack, Julian Weber, Salomon Kabongo, Elizabeth Salesky, Iroro Orife, Colin Leong, Perez Ogayo, Chris Emezue, Jonathan Mukiibi, Salomey Osei, Apelete Agbolo, Victor Akinode, Bernard Opoku, Samuel Olanrewaju, Jesujoba O. Alabi, Shamsuddeen Hassan Muhammad
2022	—	`conf`	Brazilian Portuguese Speech Recognition Using Wav2vec 2.0. PROPOR Lucas Rafael Stefanel Gris, Edresson Casanova, Frederico Santos de Oliveira, Anderson da Silva Soares, Arnaldo Cândido Júnior
2022	J	`jnl`	Interpretability Analysis of Deep Models for COVID-19 Detection. CoRR Daniel Peixoto Pinto da Silva, Edresson Casanova, Lucas Rafael Stefanel Gris, Arnaldo Cândido Júnior, Marcelo Finger, Flaviane Romani Fernandes Svartman, Beatriz Raposo de Medeiros, Marcus Vinícius Moreira Martins, Sandra Maria Aluísio, Larissa Cristina Berti, João Paulo Teixeira
2022	—	`conf`	Overview of the Automatic Speech Recognition for Spontaneous and Prepared Speech & Speech Emotion Recognition in Portuguese (S&ER) Shared-tasks at PROPOR 2022. SE&R@PROPOR Ricardo M. Marcacini, Arnaldo Cândido Jr., Edresson Casanova
2022	—	`ed.`	Proceedings of the Workshop on Automatic Speech Recognition for Spontaneous and Prepared Speech & Speech Emotion Recognition in Portuguese co-located with 15th edition of the International Conference on the Computational Processing of Portuguese (PROPOR 2022), Virtual Event, Fortaleza, Brazil, March 22, 2022. SE&R@PROPOR Ricardo M. Marcacini, Arnaldo Cândido Jr., Edresson Casanova
2022	J	`jnl`	TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese. Lang. Resour. Evaluation Edresson Casanova, Arnaldo Cândido Júnior, Christopher Shulby, Frederico Santos de Oliveira, João Paulo Ramos Teixeira, Moacir Antonelli Ponti, Sandra M. Aluísio
2022	A*	`conf`	YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for Everyone. ICML Edresson Casanova, Julian Weber, Christopher Dane Shulby, Arnaldo Cândido Júnior, Eren Gölge, Moacir A. Ponti
2021	J	`jnl`	Brazilian Portuguese Speech Recognition Using Wav2vec 2.0. CoRR Lucas Rafael Stefanel Gris, Edresson Casanova, Frederico Santos de Oliveira, Anderson da Silva Soares, Arnaldo Cândido Júnior
2021	J	`jnl`	CORAA: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese. CoRR Arnaldo Cândido Júnior, Edresson Casanova, Anderson da Silva Soares, Frederico Santos de Oliveira, Lucas Oliveira, Ricardo Corso Fernandes Junior, Daniel Peixoto Pinto da Silva, Fernando Gorgulho Fayet, Bruno Baldissera Carlotto, Lucas Rafael Stefanel Gris, Sandra Maria Aluísio
2021	—	`conf`	Deep Learning against COVID-19: Respiratory Insufficiency Detection in Brazilian Portuguese Speech. ACL/IJCNLP (Findings) Edresson Casanova, Lucas Gris, Augusto Camargo Neto, Daniel Peixoto Pinto da Silva, Murilo Gazzola, Ester C. Sabino, Anna Levin, Arnaldo Cândido Jr., Sandra M. Aluísio, Marcelo Finger
2021	—	`conf`	Evaluating Semantic Similarity Methods to Build Semantic Predictability Norms of Reading Data. TDS Sidney Evaldo Leal, Edresson Casanova, Gustavo Paetzold, Sandra M. Aluísio
2021	A	`conf`	SC-GlowTTS: An Efficient Zero-Shot Multi-Speaker Text-To-Speech Model. Interspeech Edresson Casanova, Christopher Shulby, Eren Gölge, Nicolas Michael Müller, Frederico Santos de Oliveira, Arnaldo Cândido Jr., Anderson da Silva Soares, Sandra Maria Aluísio, Moacir Antonelli Ponti
2021	J	`jnl`	SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model. CoRR Edresson Casanova, Christopher Shulby, Eren Gölge, Nicolas Michael Müller, Frederico Santos de Oliveira, Arnaldo Cândido Júnior, Anderson da Silva Soares, Sandra Maria Aluísio, Moacir Antonelli Ponti
2021	—	`conf`	Speech2Phone: A Novel and Efficient Method for Training Speaker Recognition Models. BRACIS (2) Edresson Casanova, Arnaldo Cândido Júnior, Christopher Shulby, Frederico Santos de Oliveira, Lucas Rafael Stefanel Gris, Hamilton Pereira da Silva, Sandra Maria Aluísio, Moacir Antonelli Ponti
2021	A	`conf`	Transfer Learning and Data Augmentation Techniques to the COVID-19 Identification Tasks in ComParE 2021. Interspeech Edresson Casanova, Arnaldo Cândido Jr., Ricardo Corso Fernandes Junior, Marcelo Finger, Lucas Rafael Stefanel Gris, Moacir Antonelli Ponti, Daniel Peixoto Pinto da Silva
2021	J	`jnl`	YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone. CoRR Edresson Casanova, Julian Weber, Christopher Shulby, Arnaldo Cândido Júnior, Eren Gölge, Moacir Antonelli Ponti
2020	J	`jnl`	End-To-End Speech Synthesis Applied to Brazilian Portuguese. CoRR Edresson Casanova, Arnaldo Cândido Júnior, Frederico Santos de Oliveira, Christopher Shulby, João Paulo Teixeira, Moacir Antonelli Ponti, Sandra Maria Aluísio
2020	B	`conf`	Evaluating Sentence Segmentation in Different Datasets of Neuropsychological Language Tests in Brazilian Portuguese. LREC Edresson Casanova, Marcos V. Treviso, Lilian Hübner, Sandra M. Aluísio
2020	—	`conf`	Natural Language Inference for Portuguese Using BERT and Multilingual Information. PROPOR Marco Antonio Sobrevilla Cabezudo, Marcio Lima Inácio, Ana Carolina Rodrigues, Edresson Casanova, Rogério Figueredo de Sousa
2020	J	`jnl`	Speech2Phone: A Multilingual and Text Independent Speaker Identification Model. CoRR Edresson Casanova, Arnaldo Cândido Júnior, Christopher Shulby, Hamilton Pereira da Silva, Pedro Luiz de Paula Filho, Alessandro Ferreira Cordeiro, Victor de Oliveira Guedes, Sandra Maria Aluísio
2019	—	`conf`	NILC at ASSIN 2: Exploring Multilingual Approaches. ASSIN@STIL Marco Antonio Sobrevilla Cabezudo, Marcio Lima Inácio, Ana Carolina Rodrigues, Edresson Casanova, Rogério Figueredo de Sousa