Page: 1 2 3 4 5 6 7 8... 554
61 |
Automatic Dialect Density Estimation for African American English ...
|
|
|
|
BASE
|
|
Show details
|
|
62 |
Fairly Accurate: Learning Optimal Accuracy vs. Fairness Tradeoffs for Hate Speech Detection ...
|
|
|
|
BASE
|
|
Show details
|
|
63 |
Mono vs Multilingual BERT: A Case Study in Hindi and Marathi Named Entity Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
65 |
End-to-end contextual asr based on posterior distribution adaptation for hybrid ctc/attention system ...
|
|
|
|
BASE
|
|
Show details
|
|
67 |
Large-scale Bilingual Language-Image Contrastive Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
68 |
Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
69 |
Semantic properties of English nominal pluralization: Insights from word embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
71 |
Informative Causality Extraction from Medical Literature via Dependency-tree based Patterns ...
|
|
|
|
BASE
|
|
Show details
|
|
72 |
NorDiaChange: Diachronic Semantic Change Dataset for Norwegian ...
|
|
|
|
BASE
|
|
Show details
|
|
73 |
Toxicity Detection for Indic Multilingual Social Media Content ...
|
|
|
|
BASE
|
|
Show details
|
|
74 |
Learn from Structural Scope: Improving Aspect-Level Sentiment Analysis with Hybrid Graph Convolutional Networks ...
|
|
|
|
BASE
|
|
Show details
|
|
75 |
SciNLI: A Corpus for Natural Language Inference on Scientific Text ...
|
|
|
|
BASE
|
|
Show details
|
|
76 |
SHAS: Approaching optimal Segmentation for End-to-End Speech Translation ...
|
|
|
|
Abstract:
Speech translation models are unable to directly process long audios, like TED talks, which have to be split into shorter segments. Speech translation datasets provide manual segmentations of the audios, which are not available in real-world scenarios, and existing segmentation methods usually significantly reduce translation quality at inference time. To bridge the gap between the manual segmentation of training and the automatic one at inference, we propose Supervised Hybrid Audio Segmentation (SHAS), a method that can effectively learn the optimal segmentation from any manually segmented speech corpus. First, we train a classifier to identify the included frames in a segmentation, using speech representations from a pre-trained wav2vec 2.0. The optimal splitting points are then found by a probabilistic Divide-and-Conquer algorithm that progressively splits at the frame of lowest probability until all segments are below a pre-specified length. Experiments on MuST-C and mTEDx show that the translation of ... : Submitted to Interspeech 2022, 5 pages. Previous version (v1) has additionally a 2-page Appendix ...
|
|
Keyword:
Audio and Speech Processing eess.AS; Computation and Language cs.CL; FOS Computer and information sciences; FOS Electrical engineering, electronic engineering, information engineering; Sound cs.SD
|
|
URL: https://arxiv.org/abs/2202.04774 https://dx.doi.org/10.48550/arxiv.2202.04774
|
|
BASE
|
|
Hide details
|
|
77 |
A New Framework for Fast Automated Phonological Reconstruction Using Trimmed Alignments and Sound Correspondence Patterns ...
|
|
|
|
BASE
|
|
Show details
|
|
78 |
Learning the Ordering of Coordinate Compounds and Elaborate Expressions in Hmong, Lahu, and Chinese ...
|
|
|
|
BASE
|
|
Show details
|
|
79 |
Learning to pronounce as measuring cross-lingual joint orthography-phonology complexity ...
|
|
|
|
BASE
|
|
Show details
|
|
80 |
The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checking ...
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8... 554
|
|