Alert button

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

CounterGeDi: A controllable approach to generate polite, detoxified and emotional counterspeech

May 09, 2022
Punyajoy Saha, Kanishk Singh, Adarsh Kumar, Binny Mathew, Animesh Mukherjee

Figure 1 for CounterGeDi: A controllable approach to generate polite, detoxified and emotional counterspeech
Figure 2 for CounterGeDi: A controllable approach to generate polite, detoxified and emotional counterspeech
Figure 3 for CounterGeDi: A controllable approach to generate polite, detoxified and emotional counterspeech
Figure 4 for CounterGeDi: A controllable approach to generate polite, detoxified and emotional counterspeech
Viaarxiv icon

Bandwidth-Scalable Fully Mask-Based Deep FCRN Acoustic Echo Cancellation and Postfiltering

May 09, 2022
Ernst Seidel, Rasmus Kongsgaard Olsson, Karim Haddad, Zhengyang Li, Pejman Mowlaee, Tim Fingscheidt

Figure 1 for Bandwidth-Scalable Fully Mask-Based Deep FCRN Acoustic Echo Cancellation and Postfiltering
Figure 2 for Bandwidth-Scalable Fully Mask-Based Deep FCRN Acoustic Echo Cancellation and Postfiltering
Figure 3 for Bandwidth-Scalable Fully Mask-Based Deep FCRN Acoustic Echo Cancellation and Postfiltering
Figure 4 for Bandwidth-Scalable Fully Mask-Based Deep FCRN Acoustic Echo Cancellation and Postfiltering
Viaarxiv icon

DeepSpectrumLite: A Power-Efficient Transfer Learning Framework for Embedded Speech and Audio Processing from Decentralised Data

Apr 23, 2021
Shahin Amiriparian, Tobias Hübner, Maurice Gerczuk, Sandra Ottl, Björn W. Schuller

Figure 1 for DeepSpectrumLite: A Power-Efficient Transfer Learning Framework for Embedded Speech and Audio Processing from Decentralised Data
Figure 2 for DeepSpectrumLite: A Power-Efficient Transfer Learning Framework for Embedded Speech and Audio Processing from Decentralised Data
Figure 3 for DeepSpectrumLite: A Power-Efficient Transfer Learning Framework for Embedded Speech and Audio Processing from Decentralised Data
Figure 4 for DeepSpectrumLite: A Power-Efficient Transfer Learning Framework for Embedded Speech and Audio Processing from Decentralised Data
Viaarxiv icon

Proposal-based Few-shot Sound Event Detection for Speech and Environmental Sounds with Perceivers

Jul 28, 2021
Piper Wolters, Chris Daw, Brian Hutchinson, Lauren Phillips

Figure 1 for Proposal-based Few-shot Sound Event Detection for Speech and Environmental Sounds with Perceivers
Figure 2 for Proposal-based Few-shot Sound Event Detection for Speech and Environmental Sounds with Perceivers
Figure 3 for Proposal-based Few-shot Sound Event Detection for Speech and Environmental Sounds with Perceivers
Figure 4 for Proposal-based Few-shot Sound Event Detection for Speech and Environmental Sounds with Perceivers
Viaarxiv icon

BERT-LID: Leveraging BERT to Improve Spoken Language Identification

Mar 01, 2022
Yuting Nie, Junhong Zhao, Wei-Qiang Zhang, Jinfeng Bai, Zhongqin Wu

Figure 1 for BERT-LID: Leveraging BERT to Improve Spoken Language Identification
Figure 2 for BERT-LID: Leveraging BERT to Improve Spoken Language Identification
Figure 3 for BERT-LID: Leveraging BERT to Improve Spoken Language Identification
Figure 4 for BERT-LID: Leveraging BERT to Improve Spoken Language Identification
Viaarxiv icon

Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data

Jun 08, 2022
Shohreh Deldari, Hao Xue, Aaqib Saeed, Jiayuan He, Daniel V. Smith, Flora D. Salim

Figure 1 for Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data
Figure 2 for Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data
Figure 3 for Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data
Figure 4 for Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data
Viaarxiv icon

Speech Representation Learning Combining Conformer CPC with Deep Cluster for the ZeroSpeech Challenge 2021

Jul 13, 2021
Takashi Maekaku, Xuankai Chang, Yuya Fujita, Li-Wei Chen, Shinji Watanabe, Alexander Rudnicky

Figure 1 for Speech Representation Learning Combining Conformer CPC with Deep Cluster for the ZeroSpeech Challenge 2021
Figure 2 for Speech Representation Learning Combining Conformer CPC with Deep Cluster for the ZeroSpeech Challenge 2021
Figure 3 for Speech Representation Learning Combining Conformer CPC with Deep Cluster for the ZeroSpeech Challenge 2021
Figure 4 for Speech Representation Learning Combining Conformer CPC with Deep Cluster for the ZeroSpeech Challenge 2021
Viaarxiv icon

Towards Identity Preserving Normal to Dysarthric Voice Conversion

Oct 15, 2021
Wen-Chin Huang, Bence Mark Halpern, Lester Phillip Violeta, Odette Scharenborg, Tomoki Toda

Figure 1 for Towards Identity Preserving Normal to Dysarthric Voice Conversion
Figure 2 for Towards Identity Preserving Normal to Dysarthric Voice Conversion
Figure 3 for Towards Identity Preserving Normal to Dysarthric Voice Conversion
Figure 4 for Towards Identity Preserving Normal to Dysarthric Voice Conversion
Viaarxiv icon

Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentation

May 25, 2022
Injy Hamed, Nizar Habash, Slim Abdennadher, Ngoc Thang Vu

Figure 1 for Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentation
Figure 2 for Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentation
Figure 3 for Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentation
Figure 4 for Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentation
Viaarxiv icon

End-to-End Speech Recognition from Federated Acoustic Models

Apr 29, 2021
Yan Gao, Titouan Parcollet, Javier Fernandez-Marques, Pedro P. B. de Gusmao, Daniel J. Beutel, Nicholas D. Lane

Figure 1 for End-to-End Speech Recognition from Federated Acoustic Models
Figure 2 for End-to-End Speech Recognition from Federated Acoustic Models
Figure 3 for End-to-End Speech Recognition from Federated Acoustic Models
Viaarxiv icon