CTC-internal scoring shows no WER improvement over greedy decoding on LibriSpeech, with acoustic confidence failing to correlate with linguistic plausibility. MBR decoding using RoBERTa PLL achieves a 5.42% WER, outperforming greedy decoding by 0.535 pp, demonstrating that linguistic information can overcome CTC's saturation limit.
CTC Oracle Gap: Acoustic Exhaustion and Linguistic Recovery
from English