MMSE-based channel error mitigation for distributed speech recognition
نویسندگان
چکیده
Recently, the first version of an ETSI standard for Distributed Speech Recognition has been proposed. The main benefit of this approach is the possibility of maintaining a high recognition performance when accessing remote information systems. The use of a digital channel for transmission of the encoded speech parameters implies the introduction of several channel distortions. Our paper deals with the mitigation of such distortions. We study the application of MMSE estimation to this problem and propose a new MMSE procedure that obtains the probabilities needed for MMSE from a forward-backward algorithm. We show that MMSE estimation obtains better performance than the mitigation algorithm described in the ETSI standard under different channel conditions.
منابع مشابه
HMM-based channel error mitigation and its application to distributed speech recognition
The emergence of distributed speech recognition has generated the need to mitigate the degradations that the transmission channel introduces in the speech features used for recognition. This work proposes a hidden Markov model (HMM) framework from which different mitigation techniques oriented to wireless channels can be derived. First, we study the performance of two techniques based on the us...
متن کاملMemory-enhanced MMSE-based channel error mitigation for distributed speech recognition
A new approach to sequence minimum mean-squared error (SMMSE) decoding for vector quantization over channels with memory is presented. The decoder is based on the Gilbert channel model that allows the exploitation of intra-vector correlation of bit error sequences. We apply the memory-enhanced SMMSE decoding algorithm to channel error mitigation in distributed speech recognition. Experiments on...
متن کاملSoft features for improved distributed speech recognition over wireless networks
A major drawback of distributed versus terminal-based speech recognition is the fact that transmission errors can lead to degraded recognition performance. In this paper we employ “soft features” to mitigate the effect of bit errors on wireless transmission links: At the receiver a posteriori probabilities of the transmitted feature vectors are computed by combining bit reliability information ...
متن کاملChannel-optimized Error Mitigation for Distributed Speech Recognition over Wireless Networks
This paper investigates the error mitigation algorithms for distributed speech recognition over wireless channels. A MAP symbol decoding algorithm which exploits the combined a priori information of source and channel is proposed. This is used in conjunction with a modified BCJR algorithm for decoding convolutional codes based on sectionalized code trellises. Performance is further enhanced by ...
متن کاملEntropy-optimized channel error mitigation with application to speech recognition over wireless
In this paper we propose an entropy-optimized channel error mitigation technique with a low computational complexity and moderate memory requirements, suitable for transmissions over wireless channels. We apply it to Distributed Speech Recognition (DSR), getting an improvement of around in word accuracy over the recognition performance obtained by the mitigation technique proposed in the ETSI s...
متن کامل