Room Adaptation of Training Data for Distant Speech Recognition

We present a novel signal processing-based approach for estimating room impulse responses for augmentation of ASR training data that is best suited to the reverberation characteristics in a particular acoustic space. Our approach estimates an impulse response of a room by using a supervised adaptive system identification algorithm to extract the relative transfer function between a speech source played through a loudspeaker and recorded by a microphone. These impulse responses can then be applied to clean speech files to create an augmented training set for an ASR system. Given the availability of a small amount of this type of playback audio for a room, we show that an ASR model trained with our data augmentation approach can provide a 19% relative reduction in word error rate compared to a system using random augmentation.