5 papers
HydraQE: OSU's Submission for the IWSLT 2026 Speech Translation Metrics Shared Task
Kevin Krahn, Eric Fosler-Lussier
We present HydraQE, our contribution to the IWSLT 2026 Speech Translation Metrics shared task. HydraQE is an end-to-end, reference-free quality estimation (QE) system for speech tr…
Do LLM Decoders Listen Fairly? Benchmarking How Language Model Priors Shape Bias in Speech Recognition
Srishti Ginjala, Eric Fosler-Lussier, Christopher W. Myers +1
As pretrained large language models replace task-specific decoders in speech recognition, a critical question arises: do their text-derived priors make recognition fairer or more b…
VISTA: Verification In Sequential Turn-based Assessment
Ashley Lewis, Andrew Perrault, Eric Fosler-Lussier +1
Hallucination--defined here as generating statements unsupported or contradicted by available evidence or conversational context--remains a major obstacle to deploying conversation…
Beyond Length: Context-Aware Expansion and Independence as Developmentally Sensitive Evaluation in Child Utterances
Jiyun Chun, Eric Fosler-Lussier, Michael White +1
Evaluating the quality of children's utterances in adult-child dialogue remains challenging due to insufficient context-sensitive metrics. Common proxies such as Mean Length of Utt…
End-to-End Diarization utilizing Attractor Deep Clustering
David Palzer, Matthew Maciejewski, Eric Fosler-Lussier
Speaker diarization remains challenging due to the need for structured speaker representations, efficient modeling, and robustness to varying conditions. We propose a performant, c…