Alert button

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

Retrieving Speaker Information from Personalized Acoustic Models for Speech Recognition

Nov 07, 2021
Salima Mdhaffar, Jean-François Bonastre, Marc Tommasi, Natalia Tomashenko, Yannick Estève

Figure 1 for Retrieving Speaker Information from Personalized Acoustic Models for Speech Recognition
Figure 2 for Retrieving Speaker Information from Personalized Acoustic Models for Speech Recognition
Figure 3 for Retrieving Speaker Information from Personalized Acoustic Models for Speech Recognition
Figure 4 for Retrieving Speaker Information from Personalized Acoustic Models for Speech Recognition
Viaarxiv icon

Multi-task Language Modeling for Improving Speech Recognition of Rare Words

Nov 25, 2020
Chao-Han Huck Yang, Linda Liu, Ankur Gandhe, Yile Gu, Anirudh Raju, Denis Filimonov, Ivan Bulyko

Figure 1 for Multi-task Language Modeling for Improving Speech Recognition of Rare Words
Figure 2 for Multi-task Language Modeling for Improving Speech Recognition of Rare Words
Figure 3 for Multi-task Language Modeling for Improving Speech Recognition of Rare Words
Figure 4 for Multi-task Language Modeling for Improving Speech Recognition of Rare Words
Viaarxiv icon

Enabling On-Device Training of Speech Recognition Models with Federated Dropout

Oct 07, 2021
Dhruv Guliani, Lillian Zhou, Changwan Ryu, Tien-Ju Yang, Harry Zhang, Yonghui Xiao, Francoise Beaufays, Giovanni Motta

Figure 1 for Enabling On-Device Training of Speech Recognition Models with Federated Dropout
Figure 2 for Enabling On-Device Training of Speech Recognition Models with Federated Dropout
Figure 3 for Enabling On-Device Training of Speech Recognition Models with Federated Dropout
Figure 4 for Enabling On-Device Training of Speech Recognition Models with Federated Dropout
Viaarxiv icon

SoftCTC $\unicode{x2013}$ Semi-Supervised Learning for Text Recognition using Soft Pseudo-Labels

Dec 05, 2022
Martin Kišš, Michal Hradiš, Karel Beneš, Petr Buchal, Michal Kula

Figure 1 for SoftCTC $\unicode{x2013}$ Semi-Supervised Learning for Text Recognition using Soft Pseudo-Labels
Figure 2 for SoftCTC $\unicode{x2013}$ Semi-Supervised Learning for Text Recognition using Soft Pseudo-Labels
Figure 3 for SoftCTC $\unicode{x2013}$ Semi-Supervised Learning for Text Recognition using Soft Pseudo-Labels
Figure 4 for SoftCTC $\unicode{x2013}$ Semi-Supervised Learning for Text Recognition using Soft Pseudo-Labels
Viaarxiv icon

Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language

Dec 14, 2022
Alexei Baevski, Arun Babu, Wei-Ning Hsu, Michael Auli

Figure 1 for Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language
Figure 2 for Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language
Figure 3 for Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language
Figure 4 for Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language
Viaarxiv icon

Conversational speech recognition leveraging effective fusion methods for cross-utterance language modeling

Nov 05, 2021
Bi-Cheng Yan, Hsin-Wei Wang, Shih-Hsuan Chiu, Hsuan-Sheng Chiu, Berlin Chen

Figure 1 for Conversational speech recognition leveraging effective fusion methods for cross-utterance language modeling
Figure 2 for Conversational speech recognition leveraging effective fusion methods for cross-utterance language modeling
Figure 3 for Conversational speech recognition leveraging effective fusion methods for cross-utterance language modeling
Figure 4 for Conversational speech recognition leveraging effective fusion methods for cross-utterance language modeling
Viaarxiv icon

Accent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddings

Oct 08, 2021
Jialu Li, Vimal Manohar, Pooja Chitkara, Andros Tjandra, Michael Picheny, Frank Zhang, Xiaohui Zhang, Yatharth Saraf

Figure 1 for Accent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddings
Figure 2 for Accent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddings
Figure 3 for Accent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddings
Figure 4 for Accent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddings
Viaarxiv icon

SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network

Apr 12, 2021
William Chan, Daniel Park, Chris Lee, Yu Zhang, Quoc Le, Mohammad Norouzi

Figure 1 for SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network
Figure 2 for SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network
Viaarxiv icon

FullStop:Punctuation and Segmentation Prediction for Dutch with Transformers

Jan 09, 2023
Vincent Vandeghinste, Oliver Guhr

Figure 1 for FullStop:Punctuation and Segmentation Prediction for Dutch with Transformers
Figure 2 for FullStop:Punctuation and Segmentation Prediction for Dutch with Transformers
Figure 3 for FullStop:Punctuation and Segmentation Prediction for Dutch with Transformers
Figure 4 for FullStop:Punctuation and Segmentation Prediction for Dutch with Transformers
Viaarxiv icon

Neural Architecture Search for Speech Recognition

Jul 27, 2020
Shoukang Hu, Xurong Xie, Shansong Liu, Mengzhe Geng, Xunying Liu, Helen Meng

Figure 1 for Neural Architecture Search for Speech Recognition
Figure 2 for Neural Architecture Search for Speech Recognition
Figure 3 for Neural Architecture Search for Speech Recognition
Figure 4 for Neural Architecture Search for Speech Recognition
Viaarxiv icon