Recognition of voice commands by multisource ASR and noise cancellation in a smart home environment

In this paper, we present a multisource ASR system to detect home automation orders in various everyday listening conditions in a realistic home. The system is based on a state of the art echo cancellation stage that feeds recently introduced ASR techniques. The evaluation was conducted on a realistic noisy data set acquired in a smart home where a microphone was placed near the noise source and several other microphones were placed in different rooms. This distant speech corpus was recorded with 23 speakers uttering colloquial or distress sentences as well as home automation orders. Techniques acting at the decoding stage and using a priori knowledge gave the best results in noisy condition compared to the baseline (recall= 93.2% vs 59.2%) reaching good enough performance for a real usage although improvement still need to be made when music is used as background noise.