Robust speech recognition in reverberant environments by using an optimal synthetic room impulse response model

This paper presents a practical technique for Automatic speech recognition (ASR) in multiple reverberant environment selection. Multiple ASR models are trained with artificial synthetic room impulse responses (IRs), i.e. simulated room IRs, with different reverberation time (T60Models) and tested on real room IRs with varying T60Rooms. To apply our method, the biggest challenge is to choose a proper artificial room IR model for training ASR models. In this paper, a generalised statistical IR model with attenuated reverberation after an early reflection period, named attenuated IR model, has been adopted based on three time-domain statistical IR models. Its optimal values of the reverberation-attenuation factor and the early reflection period on the recognition rate have been searched and determined. Extensive testing has been performed over four real room IR sets (63 IRs in total) with variant T60Rooms and speaker microphone distances (SMDs). The optimised attenuated IR model had the best performance in terms of recognition rate over others. Specific considerations of the practical use of the method have been taken into account including: (i) the maximal training step of T60Model in order to get the minimal number of models with acceptable performance; (ii) the impact of selection errors on the ASR caused by the estimation error of T60Room; and (iii) the performance over SMD and direct-to-reverberation energy Ratio (DRR). It is shown that recognition rates of over 80∼90% are achieved in most cases. One important advantage of the method is that T60Room can be estimated either from reverberant sound directly (Takeda et al., 2009, Falk and Chan, 2010, Löllmann et al., 2010) or from an IR measured from any point of the room as it remains constant in the same room (Kuttruff, 2000), thus it is particularly suited to mobile applications. Compared to many classical dereverberation methods, the proposed method is more suited to ASR tasks in multiple reverberant environments, such as human-robot interaction.