2 papers
eess.AS2026
From Metrics to Natural Dialogue: French Full-Duplex Benchmark for Spoken Dialogue Models
Hamid Soltani, Gilles Boulianne
Full-duplex spoken dialogue models aim to make voice agents more natural by allowing them to listen, speak, pause, and respond during ongoing conversation. However, it is not clear…
eess.AS2025
Benchmarking Large Pretrained Multilingual Models on Québec French Speech Recognition
Coralie Serrand, Gilles Boulianne, Amira Morsli
We evaluate the performance of large pretrained multilingual speech recognition models on a regional variety of French spoken in Québec, Canada, in terms of speed, word error rate…