- Read more about Automatic Depression Detection: An Emotional Audio-Textual Corpus and a GRU/BiLSTM-based Model
- Log in to post comments
- Categories:
- Read more about SleepGAN: Towards Personalized Sleep Therapy Music
- 1 comment
- Log in to post comments
8940_Yang.pdf
- Categories:
- Read more about Entrainment Analysis for Assessment of Autistic Speech Prosody Using Bottleneck Features of Deep Neural Network
- Log in to post comments
In the present study, we quantify entrainment characteristics of conversation with the aim of automatic assessment of the severity of autism spectrum disorder (ASD). We focus on pairs of utterances immediate before and after turn-takings, which have prosodic/acoustic similarities.
- Categories:
- Read more about Massive Unsourced Random Access Based on Bilinear Vector Approximate Message Passing Poster
- Log in to post comments
- Categories:
- Read more about MASSIVE UNSOURCED RANDOM ACCESS BASED ON BILINEAR VECTOR APPROXIMATE MESSAGE PASSING presentation
- Log in to post comments
- Categories:
- Read more about A KNOWLEDGE/DATA ENHANCED METHOD FOR JOINT EVENT AND TEMP RELATION EXTRACTIONORAL
- Log in to post comments
Understanding temporal relations (TempRels) between events is an important task that could benefit many downstream NLP applications. This task inevitably faces the challenges of both a limited amount of high-quality training data and a very biased distribution of TempRels. These problems will substantially hurt the performance of extraction systems because they are inclined to predict dominant TempRels when training with a limited amount of data.
- Categories:
- Read more about Provable Sample Complexity Guarantees for Learning of Continuous-Action Graphical Games with Nonparametric Utilities
- Log in to post comments
- Categories:
- Read more about Information Theoretic Limits for Standard and One-bit Compressed Sensing with Graph-structured Sparsity
- Log in to post comments
- Categories:
- Read more about Domain Generalized Few-Shot Image Classification Via Meta Regularization Network
- Log in to post comments
- Categories:
- Read more about Integration of Pre-trained Networks with Continuous Token Interface For End-to-End Spoken Language Understanding
- Log in to post comments
Most End-to-End (E2E) Spoken Language Understanding (SLU) networks leverage the pre-trained Automatic Speech Recognition (ASR) networks but still lack the capability to understand the semantics of utterances, crucial for the SLU task. To solve this, recently proposed studies use pre-trained Natural Language Understanding (NLU) networks. However, it is not trivial to fully utilize both pre-trained networks; many solutions were proposed, such as Knowledge Distillation (KD), cross-modal shared embedding, and network integration with Interface.
- Categories: