Sequential bias compensation for robust speech recognition
نویسنده
چکیده
Additive bias compensation is a simple and effective technique to overcome the performance degradation caused by acoustic mismatch in speech recognition systems. Bias is usually estimated in a batch mode, assuming that its parameters are constant for the whole utterance. This paper develops a new sequential algorithm for additive bias estimation, which can potentially track time varying mismatch effects within a test utterance. Relation to recursive KullbackLeibler technique is pointed out, and the method is tested using computer simulations and speech recognition experiments. Significant performance improvements in the recognition rate are obtained for supervised adaptation.
منابع مشابه
A robust training algorithm for adverse speech recognition
In this paper, a new robust training algorithm is proposed for the generation of a set of bias-removed, noise-suppressed reference speech HMM models in adverse environment suering from both channel bias and additive noise. Its main idea is to incorporate a signal bias-compensation operation and a PMC noise-compensation operation into its iterative training process. This makes the resulting spe...
متن کاملA robust environment-effects suppression training algorithm for adverse Mandarin speech recognition
In this paper, a new robust training algorithm for the generation of a set of bias-removed, noise-suppressed reference speech HMM models directly from a training database collected in adverse environment suffering with both convolutional channel bias and additive noise is proposed. Its main idea is to incorporate a signal biascompensation operation and a PMC noise-compensation operation into it...
متن کاملروشی جدید در بازشناسی مقاوم گفتار مبتنی بر دادگان مفقود با استفاده از شبکه عصبی دوسویه
Performance of speech recognition systems is greatly reduced when speech corrupted by noise. One common method for robust speech recognition systems is missing feature methods. In this way, the components in time - frequency representation of signal (Spectrogram) that present low signal to noise ratio (SNR), are tagged as missing and deleted then replaced by remained components and statistical ...
متن کاملResidual noise compensation by a sequential EM algorithm for robust speech recognition in nonstationary noise
We model noise as a stationary component plus a time varying residual. The stationary part is estimated off-line and compensated using Log-Add noise compensation. The time varying residual is estimated and compensated using a sequential EM algorithm. The residual noise compensation proceeds in parallel with the recognition process. Experimental results demonstrate that the proposed algorithm im...
متن کاملResidual noise compensation for robust speech recognition in nonstationary noise
We present a model-based noise compensation algorithm for robust speech recognition in nonstationary noisy environments. The effect of noise is split into a stationary part, compensated by parallel model combination, and a time varying residual. The evolution of residual noise parameters is represented by a set of state space models. The state space models are updated by Kalman prediction and t...
متن کامل