3 papers
eess.AS2024
ASASVIcomtech: The Vicomtech-UGR Speech Deepfake Detection and SASV Systems for the ASVspoof5 Challenge
Juan M. Martín-Doñas, Eros Roselló, Angel M. Gomez +3
This paper presents the work carried out by the ASASVIcomtech team, made up of researchers from Vicomtech and University of Granada, for the ASVspoof5 Challenge. The team has parti…
eess.AS2024
PolySinger: Singing-Voice to Singing-Voice Translation from English to Japanese
Silas Antonisen, Iván López-Espejo
The speech domain prevails in the spotlight for several natural language processing (NLP) tasks while the singing domain remains less explored. The culmination of NLP is the speech…
eess.AS2024
On Speech Pre-emphasis as a Simple and Inexpensive Method to Boost Speech Enhancement
Iván López-Espejo, Aditya Joglekar, Antonio M. Peinado +1
Pre-emphasis filtering, compensating for the natural energy decay of speech at higher frequencies, has been considered as a common pre-processing step in a number of speech process…