← Application Areas
Machine Learning › Application Areas ›

Data Augmentation

3622 directly classified papers

Papers per year

Papers

Comparison of Syllabification Algorithms and Training Strategies for Robust Word Count Estimation across Different Languages and Recording Conditions INTERSPEECH 2018
Training Augmentation with Adversarial Examples for Robust Speech Recognition INTERSPEECH 2018
Acoustic and Textual Data Augmentation for Improved ASR of Code-Switching Speech INTERSPEECH 2018
Talker Diarization in the Wild: the Case of Child-centered Daylong Audio-recordings INTERSPEECH 2018
User-centric Evaluation of Automatic Punctuation in ASR Closed Captioning INTERSPEECH 2018
Data Independent Sequence Augmentation Method for Acoustic Scene Classification INTERSPEECH 2018
Automatic Scoring of Shadowing Speech Based on DNN Posteriors and Their DTW INTERSPEECH 2017
Developing an Embosi (Bantu C25) Speech Variant Dictionary to Model Vowel Elision and Morpheme Deletion INTERSPEECH 2017
Data Augmentation, Missing Feature Mask and Kernel Classification for Through-the-Wall Acoustic Surveillance INTERSPEECH 2017
Occupancy Detection in Commercial and Residential Environments Using Audio Signal INTERSPEECH 2017
Exploring Fusion Methods and Feature Space for the Classification of Paralinguistic Information INTERSPEECH 2017
Automatic Evaluation of Children Reading Aloud on Sentences and Pseudowords INTERSPEECH 2017
Dominant Distortion Classification for Pre-Processing of Vowels in Remote Biomedical Voice Analysis INTERSPEECH 2017
Towards Intelligent Crowdsourcing for Audio Data Annotation: Integrating Active Learning in the Real World INTERSPEECH 2017
Training Object Class Detectors With Click Supervision CVPR 2017
Training Context-Dependent DNN Acoustic Models Using Probabilistic Sampling INTERSPEECH 2017
Improving Speech Recognizers by Refining Broadcast Data with Inaccurate Subtitle Timestamps INTERSPEECH 2017
Finding Patterns in Noisy Crowds: Regression-based Annotation Aggregation for Crowdsourced Data EMNLP 2017
Adaptive Sampling Scheme for Learning in Severely Imbalanced Large Scale Data ACML 2017
Argotario: Computational Argumentation Meets Serious Games EMNLP 2017
End-to-End Acoustic Feedback in Language Learning for Correcting Devoiced French Final-Fricatives INTERSPEECH 2017
WAT-SL: A Customizable Web Annotation Tool for Segment Labeling EACL 2017
AGA: Attribute-Guided Augmentation CVPR 2017
Colorization as a Proxy Task for Visual Understanding CVPR 2017
A Data-Driven Approach for Perceptually Validated Acoustic Features for Children’s Sibilant Fricative Productions INTERSPEECH 2017