Introduces auxiliary interference speaker loss for target-speaker ASR achieving 6.6% relative WER reduction from 18.06% to 16.87% on mixed speech.
Long short-term mem ory,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2019 2verdicts
UNVERDICTED 2representative citing papers
The authors report scalable training of neural LMs from heterogeneous corpora for ASR second-pass rescoring, delivering 6.2% relative WER reduction with minimal latency increase.
citing papers explorer
-
Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition
Introduces auxiliary interference speaker loss for target-speaker ASR achieving 6.6% relative WER reduction from 18.06% to 16.87% on mixed speech.
-
Scalable Multi Corpora Neural Language Models for ASR
The authors report scalable training of neural LMs from heterogeneous corpora for ASR second-pass rescoring, delivering 6.2% relative WER reduction with minimal latency increase.