# Edresson Casanova ## Featured Co-authors - [David Ifeoluwa Adelani](/content/profile/david-ifeoluwa-adelani/index.html) 25 publications - [Elizabeth Salesky](/content/profile/elizabeth-salesky/index.html) 22 publications - [Iroro Orife](/content/profile/iroro-orife/index.html) 15 publications - [Salomey Osei](/content/profile/salomey-osei/index.html) 14 publications - [Marcelo Finger](/content/profile/marcelo-finger/index.html) 13 publications - [Arnaldo Candido Junior](/content/profile/arnaldo-candido-junior/index.html) 12 publications - [Moacir Antonelli Ponti](/content/profile/moacir-antonelli-ponti/index.html) 12 publications - [Sandra Maria Aluisio](/content/profile/sandra-maria-aluisio/index.html) 11 publications - [Chris Emezue](/content/profile/chrisjay/index.html) 9 publications - [Jesujoba Alabi](/content/profile/jesujoba-alabi/index.html) 9 publications - [Perez Ogayo](/content/profile/perez-ogayo/index.html) 9 publications ## Research Publications ### [Evaluation of Speech Representations for MOS prediction](/content/publication/evaluation-of-speech-representations-for-mos-prediction/index.html) In this paper, we evaluate feature extraction models for predicting speech... Authors: [Frederico S. Oliveira, et al.](/content/profile/frederico-s-oliveira/index.html) ### [CML-TTS A Multilingual Dataset for Speech Synthesis in Low-Resource Languages](/content/publication/cml-tts-a-multilingual-dataset-for-speech-synthesis-in-low-resource-languages/index.html) In this paper, we present CML-TTS, a recursive acronym for CML-Multi-Lin... Authors: [Frederico S. Oliveira, et al.](/content/profile/frederico-s-oliveira/index.html) ### [Evaluating OpenAI's Whisper ASR for Punctuation Prediction and Topic Modeling of life histories of the Museum of the Person](/content/publication/evaluating-openai-s-whisper-asr-for-punctuation-prediction-and-topic-modeling-of-life-histories-of-the-museum-of-the-person/index.html) Automatic speech recognition (ASR) systems play a key role in applications... Authors: [Lucas Rafael Stefanel Gris, et al.](/content/profile/lucas-rafael-stefanel-gris/index.html) ### [Interpretability Analysis of Deep Models for COVID-19 Detection](/content/publication/interpretability-analysis-of-deep-models-for-covid-19-detection/index.html) During the outbreak of the COVID-19 pandemic, several research areas joined... Authors: [Daniel Peixoto Pinto da Silva, et al.](/content/profile/daniel-peixoto-pinto-da-silva/index.html) ### [BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus](/content/publication/bibletts-a-large-high-fidelity-multilingual-and-uniquely-african-speech-corpus/index.html) BibleTTS is a large, high-quality, open speech dataset for ten languages... Authors: [Josh Meyer, et al.](/content/profile/josh-meyer/index.html) ### [A single speaker is almost all you need for automatic speech recognition](/content/publication/a-single-speaker-is-almost-all-you-need-for-automatic-speech-recognition/index.html) We explore the use of speech synthesis and voice conversion applied to... Authors: [Edresson Casanova, et al.](/content/profile/edresson-casanova/index.html) ### [YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone](/content/publication/yourtts-towards-zero-shot-multi-speaker-tts-and-zero-shot-voice-conversion-for-everyone/index.html) YourTTS brings the power of a multilingual approach to the task of zero... Authors: [Edresson Casanova, et al.](/content/profile/edresson-casanova/index.html) ### [CORAA: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese](/content/publication/coraa-a-large-corpus-of-spontaneous-and-prepared-speech-manually-validated-for-speech-recognition-in-brazilian-portuguese/index.html) Automatic Speech recognition (ASR) is a complex and challenging task. In... Authors: [Arnaldo Candido Junior, et al.](/content/profile/arnaldo-candido-junior/index.html) ### [Brazilian Portuguese Speech Recognition Using Wav2vec 2.0](/content/publication/brazilian-portuguese-speech-recognition-using-wav2vec-2-0/index.html) Deep learning techniques have been shown to be efficient in various tasks... Authors: [Lucas Rafael Stefanel Gris, et al.](/content/profile/lucas-rafael-stefanel-gris/index.html) ### [SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model](/content/publication/sc-glowtts-an-efficient-zero-shot-multi-speaker-text-to-speech-model/index.html) In this paper, we propose SC-GlowTTS: an efficient zero-shot multi-speak... Authors: [Edresson Casanova, et al.](/content/profile/edresson-casanova/index.html) ### [End-To-End Speech Synthesis Applied to Brazilian Portuguese](/content/publication/end-to-end-speech-synthesis-applied-to-brazilian-portuguese/index.html) Voice synthesis systems are popular in different applications, such as... Authors: [Edresson Casanova, et al.](/content/profile/edresson-casanova/index.html) ### [Speech2Phone: A Multilingual and Text Independent Speaker Identification Model](/content/publication/speech2phone-a-multilingual-and-text-independent-speaker-identification-model/index.html) Voice recognition is an area with a wide application potential. Speaker... Authors: [Edresson Casanova, et al.](/content/profile/edresson-casanova/index.html)