Adding a threshold-gated paraphrase objective to a multimodal ASR model reduces WER by up to about 5 percent relative on conversational speech in Hindi, Marathi, Malayalam, Kannada, and Nyanja.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AMPS: ASR with Multimodal Paraphrase Supervision
Adding a threshold-gated paraphrase objective to a multimodal ASR model reduces WER by up to about 5 percent relative on conversational speech in Hindi, Marathi, Malayalam, Kannada, and Nyanja.