Paper Info
Title
MMSE-based channel error mitigation for distributed speech recognition
Abstract
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 recogni- tion 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 dis- tortions. 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 al- gorithm. We show that MMSE estimation obtains better per- formance than the mitigation algorithm described in the ETSI standard under different channel conditions. In this paper, we address the problem of mitigating channel errors, studying the performance of mitigation algorithms based on an MMSE (Minimum Mean Square Error) philosophy. In particular, we propose a new MMSE mitigation algorithm that utilizes correct frames received before and after the frame be- ing estimated. The different proposed techniques are develope- d using the AURORA ETSI standard front-end, although they could be straightforwardly extended to other encoding schemes. The proposed mitigation algorithms affect only to the decoding stage of the ETSI standard. For the sake of simplicity, we will assume a BPSK modulation and test two different data chan- nels (AWGN and bursty). The recognition experiments are per- formed on the Aurora-2 speech database. The paper is organized as follows. First, we briefly summa- rize the ETSI DSR standard and its error mitigation algorithm. Sections 3 and 4 are devoted to the study of several mitigation techniques over AWGN and bursty channels, respectively. Fi- nally, the conclusions of this work are summarized.
Year
Venue
Keywords
2001
INTERSPEECH
front end,minimum mean square error,information system
Field
DocType
Citations 
GSM,Speech coding,Computer science,Minimum mean square error,Communication channel,Speech recognition,Robustness (computer science),Decoding methods,Additive white Gaussian noise,Encoding (memory)
Conference
3
PageRank 
References 
Authors
0.59
3
4
Name
Order
Citations
PageRank
Antonio M. Peinado137641.97
Victoria E. Sánchez210014.72
José C. Segura348138.14
José L. Pérez-Córdoba417515.79