10 citations · 17 across the 13 of their papers we have counts for
14 papers
CVSS-X: A Multilingual Speech-to-Speech Translation Corpus for 28 Languages
Lucas Rafael Stefanel Gris, Alef Iury Siqueira Ferreira, Frederico Santos de Oliveira +4
We introduce CVSS-X, a large-scale synthetic speech-to-speech translation corpus that extends CVSS by reversing the translation direction. While CVSS translates from 21 languages i…
Cloned Voices, Real Consequences: Evaluating Bias in Political Deepfake Detection for Electoral Integrity in Brazil
Lucas Rafael Stefanel Gris, Daniel Casanova, Frederico Santos De Oliveira +4
Recent advances in generative artificial intelligence have made it easier to fabricate statements and amplify political disinformation during elections. We introduce ParlaSpoof-BR,…
Mask, Sample, Revise: A Revisable CTMC Inference Stack for Guided Discrete Flow Matching Text-to-Speech
Alef Iury Siqueira Ferreira, Lucas Rafael Stefanel Gris, Luiz Fernando de Araújo Vidal +4
Recent alignment-free non-autoregressive (NAR) text-to-speech (TTS) models formulate synthesis as a conditional infilling task, bypassing explicit duration predictors and external…
Tagarela - A Portuguese speech dataset from podcasts
Frederico Santos de Oliveira, Lucas Rafael Stefanel Gris, Alef Iury Siqueira Ferreira +8
Despite significant advances in speech processing, Portuguese remains under-resourced due to the scarcity of public, large-scale, and high-quality datasets. To address this gap, we…
Enhancing Speech Emotion Recognition with Graph-Based Multimodal Fusion and Prosodic Features for the Speech Emotion Recognition in Naturalistic Conditions Challenge at Interspeech 2025
Alef Iury Siqueira Ferreira, Lucas Rafael Gris, Alexandre Ferro Filho +7
Training SER models in natural, spontaneous speech is especially challenging due to the subtle expression of emotions and the unpredictable nature of real-world audio. In this pape…
FreeSVC: Towards Zero-shot Multilingual Singing Voice Conversion
Alef Iury Siqueira Ferreira, Lucas Rafael Gris, Augusto Seben da Rosa +6
This work presents FreeSVC, a promising multilingual singing voice conversion approach that leverages an enhanced VITS model with Speaker-invariant Clustering (SPIN) for better con…
No Saved Kaleidosope: an 100% Jitted Neural Network Coding Language with Pythonic Syntax
Augusto Seben da Rosa, Marlon Daniel Angeli, Jorge Aikes Junior +7
We developed a jitted compiler for training Artificial Neural Networks using C++, LLVM and Cuda. It features object-oriented characteristics, strong typing, parallel workers for da…
Evaluation of Speech Representations for MOS prediction
Frederico S. Oliveira, Edresson Casanova, Arnaldo Cândido Júnior +3
In this paper, we evaluate feature extraction models for predicting speech quality. We also propose a model architecture to compare embeddings of supervised learning and self-super…
Evaluating OpenAI's Whisper ASR for Punctuation Prediction and Topic Modeling of life histories of the Museum of the Person
Lucas Rafael Stefanel Gris, Ricardo Marcacini, Arnaldo Candido Junior +3
Automatic speech recognition (ASR) systems play a key role in applications involving human-machine interactions. Despite their importance, ASR models for the Portuguese language pr…
Interpretability Analysis of Deep Models for COVID-19 Detection
Daniel Peixoto Pinto da Silva, Edresson Casanova, Lucas Rafael Stefanel Gris +8
During the outbreak of COVID-19 pandemic, several research areas joined efforts to mitigate the damages caused by SARS-CoV-2. In this paper we present an interpretability analysis…
Bringing NURC/SP to Digital Life: the Role of Open-source Automatic Speech Recognition Models
Lucas Rafael Stefanel Gris, Arnaldo Candido Junior, Vinícius G. dos Santos +4
The NURC Project that started in 1969 to study the cultured linguistic urban norm spoken in five Brazilian capitals, was responsible for compiling a large corpus for each capital.…
CORAA: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese
Arnaldo Candido Junior, Edresson Casanova, Anderson Soares +8
Automatic Speech recognition (ASR) is a complex and challenging task. In recent years, there have been significant advances in the area. In particular, for the Brazilian Portuguese…
Brazilian Portuguese Speech Recognition Using Wav2vec 2.0
Lucas Rafael Stefanel Gris, Edresson Casanova, Frederico Santos de Oliveira +2
Deep learning techniques have been shown to be efficient in various tasks, especially in the development of speech recognition systems, that is, systems that aim to transcribe an a…
Speech2Phone: A Novel and Efficient Method for Training Speaker Recognition Models
Edresson Casanova, Arnaldo Candido Junior, Christopher Shulby +5
In this paper we present an efficient method for training models for speaker recognition using small or under-resourced datasets. This method requires less data than other SOTA (St…