End-to-end ASR model with speaker-specific cross-attention for two-party conversations outperforms standard models on the Switchboard corpus.
End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
We replace the Hidden Markov Model (HMM) which is traditionally used in in continuous speech recognition with a bi-directional recurrent neural network encoder coupled to a recurrent neural network decoder that directly emits a stream of phonemes. The alignment between the input and output sequences is established using an attention mechanism: the decoder emits each symbol based on a context created with a subset of input symbols elected by the attention mechanism. We report initial results demonstrating that this new approach achieves phoneme error rates that are comparable to the state-of-the-art HMM-based decoders, on the TIMIT dataset.
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.