Nearly Zero-shot Learning For Semantic Decoding In Spoken Dialogue Systems

Abstract

This paper presents two ways of dealing with scarce data in semantic decoding using N-Best speech recognition hypotheses. First, we learn features by using a deep learning architecture in which the weights for the unknown and known categories are jointly optimised. Second, an unsupervised method is used for further tuning the weights. Sharing weights injects prior knowledge to unknown categories. The unsupervised tuning (i.e. the risk minimisation) improves the F-Measure when recognising nearly zero-shot data on the DSTC3 corpus. This unsupervised method can be applied subject to two assumptions: the rank of the class marginal is assumed to be known and the class-conditional scores of the classifier are assumed to follow a Gaussian distribution.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyrojasbarahona2018nearly

Related papers

• Exploiting Sentence And Context Representations In Deep Neural Models For Spoken Language Understanding (2016)0.00
• Joint On-line Learning Of A Zero-shot Spoken Semantic Parser And A Reinforcement Learning Dialogue Manager (2018)0.00
• Unsupervised Neural And Bayesian Models For Zero-resource Speech Processing (2017)0.00
• Tackling Data Scarcity In Speech Translation Using Zero-shot Multilingual Machine Translation Techniques (2022)2.26
• Zero-shot Personalized Speech Enhancement Through Speaker-informed Model Selection (2021)7.16
• Robust Disentangled Variational Speech Representation Learning For Zero-shot Voice Conversion (2022)10.97
• Hierspeech++: Bridging The Gap Between Semantic And Acoustic Representation Of Speech By Hierarchical Variational Inference For Zero-shot Speech Synthesis (2023)6.19
• Joint Learning Of Domain Classification And Out-of-domain Detection With Dynamic Class Weighting For Satisficing False Acceptance Rates (2018)10.35