In this paper we address the problem of automatic speech recognition when wireless speech communication systems are involved. In this context, three main sources of distortion should be considered: acoustic environment, speech coding and transmission errors. Whilst the first one has already received a lot of attention, the last two deserve further investigation in our opinion. We have found out that band-pass filtering of the recognition features improves ASR performance when distortions due to these particular communication systems are present. Furthermore, we have evaluated two alternative configurations at different Bit Error Rates (BER) typical of these channels: band-pass filtering the LP-MFCC parameters or a modification of the RASTA-PLP using a sharper low-pass section perform consistently better than LP-MFCC and RASTA-PLP, respectively.

Additive noise generates important losses in automatic speech recognition systems. In this paper, we show that one of the causes contributing to these losses is the fact that conventional recognisers take into consideration feature values that are outliers. The method that we call bounded-distance HMM is a suitable method to avoid that outliers contribute to the recogniser decision. However, this method just deals with outliers, leaving the remaining features unaltered. In contrast, spectral subtraction is able to correct all the features at the expense of introducing some artifacts that, as shown in the paper, cause a larger number of outliers. As a result, we find that bounded-distance HMM and spectral subtraction complement each other well. A comprehensive experimental evaluation was conducted, considering several well-known ASR tasks (of different complexities) and numerous noise types and SNRs. The achieved results show that the suggested combination generally outperforms both the bounded-distance HMM and spectral subtraction individually. Furthermore, the obtained improvements, especially for low and medium SNRs, are larger than the sum of the improvements individually obtained by bounded-distance HMM and spectral subtraction.

In this paper, we have tackled the problem of noisy speech recognition. In particular, we have presented a novel approach to the design of filters for processing the modulation spectrum, that we have called linear equalization. We postulate that, as long as the distortion of the spectral parameters due to noise can he modeled as linear, an advantageous solution consists on estimating this linear perturbation system and designing its inverse system (the equalizer). Our experimental results show that the proposed method is very effective for three of the five considered noises.

No abstract

No abstract