Optimizing DNN Adaptation for Recognition of Enhanced Speech
نویسندگان
چکیده
Speech enhancement directly using deep neural network (DNN) is of major interest due to the capability of DNN to tangibly reduce the impact of noisy conditions in speech recognition tasks. Similarly, DNN based acoustic model adaptation to new environmental conditions is another challenging topic. In this paper we present an analysis of acoustic model adaptation in presence of a disjoint speech enhancement component, identifying an optimal setting for improving the speech recognition performance. Adaptation is derived from a consolidated technique that introduces in the training process a regularization term to prevent overfitting. We propose to optimize the adaptation of the clean acoustic models towards the enhanced speech by tuning the regularization term based on the degree of enhancement. Experiments on a popular noisy dataset (e.g., AURORA-4) demonstrate the validity of the proposed approach.
منابع مشابه
Off-line Arabic Handwritten Recognition Using a Novel Hybrid HMM-DNN Model
In order to facilitate the entry of data into the computer and its digitalization, automatic recognition of printed texts and manuscripts is one of the considerable aid to many applications. Research on automatic document recognition started decades ago with the recognition of isolated digits and letters, and today, due to advancements in machine learning methods, efforts are being made to iden...
متن کاملImproving Phoneme Sequence Recognition using Phoneme Duration Information in DNN-HSMM
Improving phoneme recognition has attracted the attention of many researchers due to its applications in various fields of speech processing. Recent research achievements show that using deep neural network (DNN) in speech recognition systems significantly improves the performance of these systems. There are two phases in DNN-based phoneme recognition systems including training and testing. Mos...
متن کاملUncertainty Decoding with Adaptive Sampling for Noise Robust DNN-Based Acoustic Modeling
Although deep neural network (DNN) based acoustic models have obtained remarkable results, the automatic speech recognition (ASR) performance still remains low in noise and reverberant conditions. To address this issue, a speech enhancement front-end is often used before recognition to reduce noise. However, the front-end cannot fully suppress noise and often introduces artifacts that are limit...
متن کاملJoint adaptation and adaptive training of TVWR for robust automatic speech recognition
Context-dependent Deep Neural Network has obtained consistent and significant improvements over the Gaussian Mixture Model (GMM) based systems for various speech recognition tasks. However, since DNN is discriminatively trained, it is more sensitive to label errors and is not reliable for unsupervised adaptation. Moreover, DNN parameters do not have a clear and meaningful interpretation, theref...
متن کاملSpeech dereverberation for enhancement and recognition using dynamic features constrained deep neural networks and feature adaptation
This paper investigates deep neural networks (DNN) based on nonlinear feature mapping and statistical linear feature adaptation approaches for reducing reverberation in speech signals. In the nonlinear feature mapping approach, DNN is trained from parallel clean/distorted speech corpus to map reverberant and noisy speech coefficients (such as log magnitude spectrum) to the underlying clean spee...
متن کامل