Alert button

"speech recognition": models, code, and papers
Alert button

Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties

Apr 04, 2021
Kathleen Siminyu, Xinjian Li, Antonios Anastasopoulos, David Mortensen, Michael R. Marlo, Graham Neubig

Figure 1 for Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties
Figure 2 for Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties
Figure 3 for Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties
Figure 4 for Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties
Viaarxiv icon

Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speech

Jan 21, 2021
Takuya Fujimura, Yuma Koizumi, Kohei Yatabe, Ryoichi Miyazaki

Figure 1 for Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speech
Figure 2 for Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speech
Figure 3 for Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speech
Figure 4 for Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speech
Viaarxiv icon

TransfoRNN: Capturing the Sequential Information in Self-Attention Representations for Language Modeling

Apr 04, 2021
Tze Yuang Chong, Xuyang Wang, Lin Yang, Junjie Wang

Figure 1 for TransfoRNN: Capturing the Sequential Information in Self-Attention Representations for Language Modeling
Figure 2 for TransfoRNN: Capturing the Sequential Information in Self-Attention Representations for Language Modeling
Figure 3 for TransfoRNN: Capturing the Sequential Information in Self-Attention Representations for Language Modeling
Figure 4 for TransfoRNN: Capturing the Sequential Information in Self-Attention Representations for Language Modeling
Viaarxiv icon

Text Augmentation for Language Models in High Error Recognition Scenario

Nov 11, 2020
Karel Beneš, Lukáš Burget

Figure 1 for Text Augmentation for Language Models in High Error Recognition Scenario
Figure 2 for Text Augmentation for Language Models in High Error Recognition Scenario
Figure 3 for Text Augmentation for Language Models in High Error Recognition Scenario
Figure 4 for Text Augmentation for Language Models in High Error Recognition Scenario
Viaarxiv icon

Improving N-gram Language Models with Pre-trained Deep Transformer

Nov 22, 2019
Yiren Wang, Hongzhao Huang, Zhe Liu, Yutong Pang, Yongqiang Wang, ChengXiang Zhai, Fuchun Peng

Figure 1 for Improving N-gram Language Models with Pre-trained Deep Transformer
Figure 2 for Improving N-gram Language Models with Pre-trained Deep Transformer
Figure 3 for Improving N-gram Language Models with Pre-trained Deep Transformer
Figure 4 for Improving N-gram Language Models with Pre-trained Deep Transformer
Viaarxiv icon

Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese

May 21, 2022
Kurt Micallef, Albert Gatt, Marc Tanti, Lonneke van der Plas, Claudia Borg

Figure 1 for Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese
Figure 2 for Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese
Figure 3 for Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese
Figure 4 for Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese
Viaarxiv icon

Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks

May 02, 2021
Siddharth Dalmia, Brian Yan, Vikas Raunak, Florian Metze, Shinji Watanabe

Figure 1 for Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks
Figure 2 for Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks
Figure 3 for Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks
Figure 4 for Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks
Viaarxiv icon

End-to-end training of time domain audio separation and recognition

Dec 25, 2019
Thilo von Neumann, Keisuke Kinoshita, Lukas Drude, Christoph Boeddeker, Marc Delcroix, Tomohiro Nakatani, Reinhold Haeb-Umbach

Figure 1 for End-to-end training of time domain audio separation and recognition
Figure 2 for End-to-end training of time domain audio separation and recognition
Figure 3 for End-to-end training of time domain audio separation and recognition
Figure 4 for End-to-end training of time domain audio separation and recognition
Viaarxiv icon

Investigation of Large-Margin Softmax in Neural Language Modeling

May 20, 2020
Jingjing Huo, Yingbo Gao, Weiyue Wang, Ralf Schlüter, Hermann Ney

Figure 1 for Investigation of Large-Margin Softmax in Neural Language Modeling
Figure 2 for Investigation of Large-Margin Softmax in Neural Language Modeling
Figure 3 for Investigation of Large-Margin Softmax in Neural Language Modeling
Figure 4 for Investigation of Large-Margin Softmax in Neural Language Modeling
Viaarxiv icon

Federated Marginal Personalization for ASR Rescoring

Dec 01, 2020
Zhe Liu, Fuchun Peng

Figure 1 for Federated Marginal Personalization for ASR Rescoring
Figure 2 for Federated Marginal Personalization for ASR Rescoring
Figure 3 for Federated Marginal Personalization for ASR Rescoring
Figure 4 for Federated Marginal Personalization for ASR Rescoring
Viaarxiv icon