Data Augmentation for Robust Keyword Spotting under Playback Interference

Abstract

Accurate on-device keyword spotting (KWS) with low false accept and false reject rate is crucial to customer experience for far-field voice control of conversational agents. It is particularly challenging to maintain low false reject rate in real world conditions where there is (a) ambient noise from external sources such as TV, household appliances, or other speech that is not directed at the device (b) imperfect cancellation of the audio playback from the device, resulting in residual echo, after being processed by the Acoustic Echo Cancellation (AEC) system. In this paper, we propose a data augmentation strategy to improve keyword spotting performance under these challenging conditions. The training set audio is artificially corrupted by mixing in music and TV/movie audio, at different signal to interference ratios. Our results show that we get around 30-45% relative reduction in false reject rates, at a range of false alarm rates, under audio playback from such devices.

Cited by in corpus (11)

• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
• Frequency Domain Multi-channel Acoustic Modeling for Distant Speech Recognition
• Gesture Recognition for FMCW Radar on the Edge
• Unacceptable, where is my privacy? Exploring Accidental Triggers of Smart Speakers
• Training Keyword Spotters with Limited and Synthesized Speech Data
• Exploiting Spectral Augmentation for Code-Switched Spoken Language Identification
• SpecAugment on Large Scale Datasets
• Behavior of Keyword Spotting Networks Under Noisy Conditions
• Towards Data-efficient Modeling for Wake Word Spotting
• SapAugment: Learning A Sample Adaptive Policy for Data Augmentation
• On Front-end Gain Invariant Modeling for Wake Word Spotting