Speaker Anonymization Using Neural Audio Codec Language Models.
Michele PanarielloFrancesco NespoliMassimiliano TodiscoNicholas W. D. EvansPublished in: ICASSP (2024)
Keyphrases
- language model
- speech recognition
- audio visual
- speaker identification
- language modeling
- prosodic features
- n gram
- probabilistic model
- automatic speech recognition
- document retrieval
- automatic transcription
- retrieval model
- query expansion
- broadcast news
- language modelling
- information retrieval
- speaker verification
- multi modal
- multimedia
- context sensitive
- visual information
- speech signal
- speaker diarization
- ad hoc information retrieval
- test collection
- relevance model
- mixture model
- vector space model
- audio features
- language model for information retrieval
- statistical language models
- visual data
- smoothing methods
- translation model
- query terms
- pseudo relevance feedback
- feature selection