Content-Context Factorized Representations for Automated Speech Recognition
This addresses generalization issues in automated speech recognition by reducing unwanted context effects, though it is incremental as it builds on existing encoder methods.
The paper tackled the problem of spurious context information in speech recognition features by introducing an unsupervised method to factor representations into content and context components, resulting in improved performance on standard benchmarks and noisy scenarios.
Deep neural networks have largely demonstrated their ability to perform automated speech recognition (ASR) by extracting meaningful features from input audio frames. Such features, however, may consist not only of information about the spoken language content, but also may contain information about unnecessary contexts such as background noise and sounds or speaker identity, accent, or protected attributes. Such information can directly harm generalization performance, by introducing spurious correlations between the spoken words and the context in which such words were spoken. In this work, we introduce an unsupervised, encoder-agnostic method for factoring speech-encoder representations into explicit content-encoding representations and spurious context-encoding representations. By doing so, we demonstrate improved performance on standard ASR benchmarks, as well as improved performance in both real-world and artificially noisy ASR scenarios.