An improved uncertainty decoding scheme with weighted samples for DNN-HMM hybrid systems
In this paper, we advance a recently-proposed uncertainty decoding scheme for DNN-HMM (deep neural network - hidden Markov model) hybrid systems. This numerical sampling concept averages DNN outputs produced by a finite set of feature samples (drawn from a probabilistic distortion model) to approximate the posterior likelihoods of the context-dependent HMM states. As main innovation, we propose a weighted DNN-output averaging based on a minimum classification error criterion and apply it to a probabilistic distortion model for spatial diffuseness features. The experimental evaluation is performed on the 8-channel REVERB Challenge task using a DNN-HMM hybrid system with multichannel front-end signal enhancement. We show that the recognition accuracy of the DNN-HMM hybrid system improves by incorporating uncertainty decoding based on random sampling and that the proposed weighted DNN-output averaging further reduces the word error rate scores.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationSimilar Papers 제목 키워드 기반
Informed Bootstrap Augmentation Improves EEG Decoding
Electroencephalography (EEG) offers detailed access to neural dynamics but remains constrained by noise and trial-by-trial variability, limiting decoding performance in data-restricted or complex paradigms. Data augmenta…
Data AugmentationEeg DecodingUncertainty-weighted Loss Functions for Improved Adversarial Attacks on Semantic Segmentation
State-of-the-art deep neural networks have been shown to be extremely powerful in a variety of perceptual tasks like semantic segmentation. However, these networks are vulnerable to adversarial perturbations of the input…
Image SegmentationSegmentationSemantic SegmentationImproved User Identification through Calibrated Monte-Carlo Dropout
This paper presents an enhanced approach to user identification using smartphone and wearable sensor data. Our methodology involves segmenting input data and independently analyzing subsequences with CNNs. During testing…
Classifier calibrationUncertainty QuantificationUser IdentificationModel Merging by Uncertainty-Based Gradient Matching
Models trained on different datasets can be merged by a weighted-averaging of their parameters, but why does it work and when can it fail? Here, we connect the inaccuracy of weighted-averaging to mismatches in the gradie…
modelTask ArithmeticExpectation Maximization Aided Modified Weighted Sequential Energy Detector for Distributed Cooperative Spectrum Sensing
Energy detector (ED) is a popular choice for distributed cooperative spectrum sensing because it does not need to be cognizant of the primary user (PU) signal characteristics. However, the conventional ED-based sensing u…