The paper combines machine speech chain text-to-speech replay with gradient episodic memory to let an ASR model learn a noisy speech task without forgetting clean speech, reporting a 40% average CER reduction over fine-tuning on LJ Speech.
These three stages, depicted in Figure 1, build upon the process proposed in [9], for the first and second stages, with our continual learning method introduced in the third stage
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Continual Learning in Machine Speech Chain Using Gradient Episodic Memory
The paper combines machine speech chain text-to-speech replay with gradient episodic memory to let an ASR model learn a noisy speech task without forgetting clean speech, reporting a 40% average CER reduction over fine-tuning on LJ Speech.