Learning Label Embeddings for Nearest-Neighbor Multi-class Classification with an Application to Speech Recognition
We consider the problem of using nearest neighbor methods to provide a conditional probability estimate, P(y|a), when the number of labels y is large and the labels share some underlying structure. We propose a method for learning error-correcting output codes (ECOCs) to model the similarity between labels within a nearest neighbor framework. The learned ECOCs and nearest neighbor information are used to provide conditional probability estimates. We apply these estimates to the problem of acoustic modeling for speech recognition. We demonstrate an absolute reduction in word error rate (WER) of 0.9% (a 2.5% relative reduction in WER) on a lecture recognition task over a state-of-the-art baseline GMM model.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationMulti-class Classificationspeech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Approximate Nearest Neighbor Search with Window Filters
We define and investigate the problem of $\textit{c-approximate window search}$: approximate nearest neighbor search where each point in the dataset has a numeric label, and the goal is to find nearest neighbors to queri…
Image RetrievalPEARL: Prototype-Enhanced Alignment for Label-Efficient Representation Learning with Deployment-Driven Insights from Digital Governance Communication Systems
In many deployed systems, new text inputs are handled by retrieving similar past cases, for example when routing and responding to citizen messages in digital governance platforms. When these systems fail, the problem is…
Representation LearningMulti-View Semi-Supervised Label Distribution Learning with Local Structure Complementarity
Label distribution learning (LDL) is a paradigm that each sample is associated with a label distribution. At present, the existing approaches are proposed for the single-view LDL problem with labeled data, while the mult…
Graph LearningOn the Resistance of Nearest Neighbor to Random Noisy Labels
Nearest neighbor has always been one of the most appealing non-parametric approaches in machine learning, pattern recognition, computer vision, etc. Previous empirical studies partly shows that nearest neighbor is resist…
A Multilabel Classification Framework for Approximate Nearest Neighbor Search
Both supervised and unsupervised machine learning algorithms have been used to learn partition-based index structures for approximate nearest neighbor (ANN) search. Existing supervised algorithms formulate the learning t…
ClassificationGeneral ClassificationMulti-Label Classification