FiLM speaker conditioning allows a SpeechLLM to adapt to pathological speakers competitively with fine-tuning while keeping general performance.
Speaker adaptation for wav2vec2 based dysarthric asr,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FiLM-Based Speaker Conditioning of a SpeechLLM for Pathological Speech Recognition
FiLM speaker conditioning allows a SpeechLLM to adapt to pathological speakers competitively with fine-tuning while keeping general performance.