Front-end improvements to reduce stationary & variable channel and noise distortions in continuous speech recognition tasks
نویسندگان
چکیده
This paper introduces our actual work in front-end techniques to obtain robust speech recognition devices in mismatch conditions (additive noise mismatch and channel mismatch). Two algorithms have been combined to compensate the distortions due to different channel characteristics and additive noise: 1) A Cepstral Mean Normalization and Variance Scaling technique (MNVS) and 2) An Adaptive Gaussian Attenuation algorithm (AGA). Combining both techniques the channel distortion effects were reduced to 90% on the HTIMIT task and the additive noise effects were reduced to 80% on the TIMIT task corrupted with additive car noise.
منابع مشابه
Noise reduction by paired-microphones using spectral subtraction
This paper proposes a method of noise reduction by pairedmicrophones as a front-end processor for speech recognition systems. This method estimates noises using a subtractive microphone array and subtracts them from the noisy speech signal using the Spectral Subtraction (SS). Since this method can estimate noises analytically and frame by frame, it is easy to estimate noises not depending on th...
متن کاملDual-microphone Robust Front-end for Arm’s-length Speech Recognition
This paper describes a novel method of improving the performance of a speech recognition front-end in non-stationary background noise. A two-microphone array has been designed that both enhances the speech and provides a continuous estimate of the background noise. This processing has been integrated with the standard ETSI DSR Advanced Front End so that the continuous noise estimate is an input...
متن کاملNormalized Autocorrelation based Features for Robust Speech Recognition in Context with Noisy Environment
This paper presents a robust approach for an automatic speech recognition system (ASR) when both additive and convolutional noises corrupt the speech signal. Robust features are derived by assuming that the corrupting noise is stationary and the channel effect is fixed during the utterance. In the proposed method the effect of additive and convolutional distortions are minimized by two stage fi...
متن کاملA Unified Approach of Compensation and Soft Masking Incorporating a Statistical Model into the Wiener Filter
In this paper, we present a new single-channel noise reduction method that integrates compensation and soft masking into the same statistical model assumptions for noise-robust speech recognition. By utilizing a Gaussian mixture model(GMM) as a pre-knowledge of speech and added noise signals, the proposed method can effectively restore clean speech spectra and separate out ambient noises from a...
متن کاملEvaluation of ETSI advanced DSR front-end and bias removal method on the Japanese newspaper article sentences speech corpus
In October 2002, European Telecommunications Standards Institute (ETSI) recommended a standard Distributed Speech Recognition (DSR) advanced front-end, ETSI ES202 050 version 1.1.1 (ES202). Many studies use this front-end in noise environments on several languages on connected digit recognition tasks. However, we have not seen the reports of large vocabulary continuous speech recognition using ...
متن کامل