Contextual Speech Recognition with Difficult Negative Training Examples
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.