Signal bias removal using the multi-path stochastic equalization technique
نویسندگان
چکیده
We propose using Hidden Markov Models (HMMs) associated with the cepstrum coefficients as a speech signal model in order to perform equalization or noise removal. The MUlti-path Stochastic Equalization (MUSE) framework allows one to process data at the frame level: it is an on-line adaptation of the model. More precisely, we apply this technique to perform bias removal in the cepstral domain in order to increase the robustness of automatic speech recognizers. Recognition experiments on two databases recorded on both PSN and GSM networks show the efficiency of the proposed method.
منابع مشابه
Towards Introducing Long-term Statistics in Muse for Robust Speech Recognition
In this paper, we propose new developments of the MUltipath Stochastic Equalization techniques (MUSE). The MUSE technique is based on an enriched model of speech, composed of both a classical model of clean speech with HMM and equalization functions. This technique is able to reduce the recognition error rate due to a mismatch between the training and testing conditions. In order to track long-...
متن کاملروشی نوین در کاهش نوفه رایسین از مقدار بزرگی سیگنال دیفیوژن در تصویربرداری تشدید مغناطیسی (MRI)
The true MR signal intensity extracted from noisy MR magnitude images is biased with the Rician noise caused by noise rectification in the magnitude calculation for low intensity pixels. This noise is more problematic when a quantitative analysis is performed based on the magnitude images with low SNR(<3.0). In such cases, the received signal for both the real and imaginary components will fluc...
متن کاملVector Equalization in Hidden Markov Models
Speech recognizers often experience serious performance degradation when d ployed in an unknown acoustic (particularly, noise contaminated) environment. To combat this problem, we proposed in a previous study a distortion measure that takes into account the norm shrinkage bias in the noisy cepstrum. In this paper, we incorporate a first order equalization mechanism, specifically aiming at avoid...
متن کاملHidden Markov models with first-order equalization for noisy speech recognition
Speech recognizers often experience serious performance degradation when deployed in an unknown acoustic (particularly, noise contaminated) environment. To combat this problem, we proposed in a previous study a family of new distortion measures that were shown to be able to withstand additive white noise without requiring 1) explicit knowledge of the noise, 2) noise reduction provisions, or 3) ...
متن کاملAn importance sampling technique for a symbol-by-symbol TCM decoding/equalization algorithm
An importance sampling simulation technique is used to estimate the bit-error rate (BER) of a symbol-by-symbol trelliscoded modulation (TCM) decoder/equalizer proposed for digital microwave radio applications. To evaluate the performance at a BER smaller than 10 , we investigate a randomized bias technique previously developed by the authors. To properly select the bias vectors, the asymptotic ...
متن کامل