End-to-end ASR model with speaker-specific cross-attention for two-party conversations outperforms standard models on the Switchboard corpus.
Contextual Speech Recognition with Difficult Negative Training Examples
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Improving the representation of contextual information is key to unlocking the potential of end-to-end (E2E) automatic speech recognition (ASR). In this work, we present a novel and simple approach for training an ASR context mechanism with difficult negative examples. The main idea is to focus on proper nouns (e.g., unique entities such as names of people and places) in the reference transcript, and use phonetically similar phrases as negative examples, encouraging the neural model to learn more discriminative representations. We apply our approach to an end-to-end contextual ASR model that jointly learns to transcribe and select the correct context items, and show that our proposed method gives up to $53.1\%$ relative improvement in word error rate (WER) across several benchmarks.
fields
eess.AS 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
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.