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

Abstract

This paper presents a practical technique for Automatic speech recognition (ASR) in multiple reverberant environments based on multi-model selection. Multiple ASR models are trained with artificial synthetic room impulse responses (IRs), i.e. simulated room IRs, with different reverberation time (T Model 60 s) and tested on real room IRs with varying T Room 60 s. 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 T Room 60 s 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 T Model 60 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 T Room 60; and iii) the performance over SMD and direct-toreverberation energy Ratio (DRR). It is shown that recognition rates of over

A Single-Channel Non-Intrusive C50 Estimator Correlated With Speech Recognition Performance

“…Additionally, several room acoustic parameters have been applied in different dereverberation methods to suppress the reverberation in the signal. C 50 is used in [9] [10] and T 60 in [11] [12] to select the ASR acoustic model that better represents the reverberant conditions of the input utterance. In [13] T 60 is used to add to the current hidden Markov model state the contribution of previous states by applying a piecewise energy decay curve that is separated in early reflections and late reverberation contributions.…”

Enhanced Robot Speech Recognition Using Biomimetic Binaural Sound Source Localization

“…These results are an important extension from our previous work in static SSL and support the robustness of the system to the sound dynamics in real-world environments. Furthermore, our system can be easily integrated with recent methods to enhance ASR in reverberant environments [55]- [57] without adding computational cost. This is the intrinsic advantage of embodied embedded cognition.…”

Study of Generalized Phase Spectrum Time Delay Estimation Method for Source Positioning in Small Room Acoustic Environment

“…The image model method, first proposed in [ 19 ], is the most widespread among the latter. Alternatively, statistical methods [ 20 ] or methods based on geometric acoustics and ray tracing [ 21 ] can be used. To create realistic sound signals in this work, the image model method was used in the implementation of Lehman, Johansson and Nordholm [ 22 , 23 ].…”