End-to-end ASR model with speaker-specific cross-attention for two-party conversations outperforms standard models on the Switchboard corpus.
Joint ctc-attention based end- to-end speech recognition using multi-task learning,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
eess.AS 2years
2019 2verdicts
UNVERDICTED 2representative citing papers
End-to-end ASR for code-switched Hindi-English with <50 hours of data shows gains from multi-task learning and corpus balancing but underperforms cascaded baselines.
citing papers explorer
-
Cross-Attention End-to-End ASR for Two-Party Conversations
End-to-end ASR model with speaker-specific cross-attention for two-party conversations outperforms standard models on the Switchboard corpus.
-
End-to-End ASR for Code-switched Hindi-English Speech
End-to-end ASR for code-switched Hindi-English with <50 hours of data shows gains from multi-task learning and corpus balancing but underperforms cascaded baselines.