A data augmentation pipeline combining LLM text rewriting with zero-shot TTS cloning of hard-acoustic prompts achieves relative WER reductions on LibriSpeech and reduces speaker/gender bias.
Attention-based models for speech recognition,
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
-
Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM
A data augmentation pipeline combining LLM text rewriting with zero-shot TTS cloning of hard-acoustic prompts achieves relative WER reductions on LibriSpeech and reduces speaker/gender bias.