End-to-End Keyword Search Based on Attention and Energy Scorer for Low Resource Languages

2020 ◽  
Author(s):  
Zeyu Zhao ◽  
Wei-Qiang Zhang
Keyword(s):  
Keyword Search ◽  
Low Resource ◽  
End To End

End-to-end speech recognition and keyword search on low-resource languages

2017 ◽  
Author(s):  
Andrew Rosenberg ◽  
Kartik Audhkhasi ◽  
Abhinav Sethy ◽  
Bhuvana Ramabhadran ◽  
Michael Picheny
Keyword(s):  
Speech Recognition ◽  
Keyword Search ◽  
Low Resource ◽  
End To End

scholarly journals Dynamic Acoustic Unit Augmentation with BPE-Dropout for Low-Resource End-to-End Speech Recognition

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3063
Author(s):  
Aleksandr Laptev ◽  
Andrei Andrusenko ◽  
Ivan Podluzhny ◽  
Anton Mitrofanov ◽  
Ivan Medennikov ◽  
...  
Keyword(s):  
Speech Recognition ◽  
Error Rate ◽  
Rapid Development ◽  
Computational Cost ◽  
Vocabulary Size ◽  
Word Error Rate ◽  
Low Resource ◽  
Steady Improvement ◽  
End To End ◽  
Asr System

With the rapid development of speech assistants, adapting server-intended automatic speech recognition (ASR) solutions to a direct device has become crucial. For on-device speech recognition tasks, researchers and industry prefer end-to-end ASR systems as they can be made resource-efficient while maintaining a higher quality compared to hybrid systems. However, building end-to-end models requires a significant amount of speech data. Personalization, which is mainly handling out-of-vocabulary (OOV) words, is another challenging task associated with speech assistants. In this work, we consider building an effective end-to-end ASR system in low-resource setups with a high OOV rate, embodied in Babel Turkish and Babel Georgian tasks. We propose a method of dynamic acoustic unit augmentation based on the Byte Pair Encoding with dropout (BPE-dropout) technique. The method non-deterministically tokenizes utterances to extend the token’s contexts and to regularize their distribution for the model’s recognition of unseen words. It also reduces the need for optimal subword vocabulary size search. The technique provides a steady improvement in regular and personalized (OOV-oriented) speech recognition tasks (at least 6% relative word error rate (WER) and 25% relative F-score) at no additional computational cost. Owing to the BPE-dropout use, our monolingual Turkish Conformer has achieved a competitive result with 22.2% character error rate (CER) and 38.9% WER, which is close to the best published multilingual system.

scholarly journals End-to-end statistical machine translation with zero or small parallel texts

2016 ◽  
Vol 22 (4) ◽  
pp. 517-548 ◽  
Author(s):  
ANN IRVINE ◽  
CHRIS CALLISON-BURCH
Keyword(s):  
Detailed Analysis ◽  
Machine Translation ◽  
Statistical Machine Translation ◽  
Parallel Corpora ◽  
Low Resource ◽  
Bilingual Lexicon ◽  
Orthographic Similarity ◽  
Discriminative Model ◽  
End To End ◽  
Parallel Texts

AbstractWe use bilingual lexicon induction techniques, which learn translations from monolingual texts in two languages, to build an end-to-end statistical machine translation (SMT) system without the use of any bilingual sentence-aligned parallel corpora. We present detailed analysis of the accuracy of bilingual lexicon induction, and show how a discriminative model can be used to combine various signals of translation equivalence (like contextual similarity, temporal similarity, orthographic similarity and topic similarity). Our discriminative model produces higher accuracy translations than previous bilingual lexicon induction techniques. We reuse these signals of translation equivalence as features on a phrase-based SMT system. These monolingually estimated features enhance low resource SMT systems in addition to allowing end-to-end machine translation without parallel corpora.

Low-resource open vocabulary keyword search using point process models

2014 ◽  
Author(s):  
Chunxi Liu ◽  
Aren Jansen ◽  
Guoguo Chen ◽  
Keith Kintzley ◽  
Jan Trmal ◽  
...  
Keyword(s):  
Point Process ◽  
Keyword Search ◽  
Process Models ◽  
Low Resource ◽  
Point Process Models

scholarly journals DeepVar: An End-to-End Deep Learning Approach for Genomic Variant Recognition in Biomedical Literature

2020 ◽  
Vol 34 (01) ◽  
pp. 598-605
Author(s):  
Chaoran Cheng ◽  
Fei Tan ◽  
Zhi Wei
Keyword(s):  
Deep Learning ◽  
Large Data ◽  
Biomedical Literature ◽  
Entity Recognition ◽  
Learning Approach ◽  
Learning Approaches ◽  
Genomic Variants ◽  
Low Resource ◽  
End To End ◽  
Genomic Variant

We consider the problem of Named Entity Recognition (NER) on biomedical scientific literature, and more specifically the genomic variants recognition in this work. Significant success has been achieved for NER on canonical tasks in recent years where large data sets are generally available. However, it remains a challenging problem on many domain-specific areas, especially the domains where only small gold annotations can be obtained. In addition, genomic variant entities exhibit diverse linguistic heterogeneity, differing much from those that have been characterized in existing canonical NER tasks. The state-of-the-art machine learning approaches heavily rely on arduous feature engineering to characterize those unique patterns. In this work, we present the first successful end-to-end deep learning approach to bridge the gap between generic NER algorithms and low-resource applications through genomic variants recognition. Our proposed model can result in promising performance without any hand-crafted features or post-processing rules. Our extensive experiments and results may shed light on other similar low-resource NER applications.

Sign in / Sign up

Export Citation Format

Share Document