Alert button

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

End-to-End Joint Target and Non-Target Speakers ASR

Jun 04, 2023
Ryo Masumura, Naoki Makishima, Taiga Yamane, Yoshihiko Yamazaki, Saki Mizuno, Mana Ihori, Mihiro Uchida, Keita Suzuki, Hiroshi Sato, Tomohiro Tanaka, Akihiko Takashima, Satoshi Suzuki, Takafumi Moriya, Nobukatsu Hojo, Atsushi Ando

Figure 1 for End-to-End Joint Target and Non-Target Speakers ASR
Figure 2 for End-to-End Joint Target and Non-Target Speakers ASR
Figure 3 for End-to-End Joint Target and Non-Target Speakers ASR
Viaarxiv icon

Model-Agnostic Meta-Learning for Multilingual Hate Speech Detection

Mar 04, 2023
Md Rabiul Awal, Roy Ka-Wei Lee, Eshaan Tanwar, Tanmay Garg, Tanmoy Chakraborty

Figure 1 for Model-Agnostic Meta-Learning for Multilingual Hate Speech Detection
Figure 2 for Model-Agnostic Meta-Learning for Multilingual Hate Speech Detection
Figure 3 for Model-Agnostic Meta-Learning for Multilingual Hate Speech Detection
Figure 4 for Model-Agnostic Meta-Learning for Multilingual Hate Speech Detection
Viaarxiv icon

Cross-lingual Knowledge Transfer and Iterative Pseudo-labeling for Low-Resource Speech Recognition with Transducers

May 23, 2023
Jan Silovsky, Liuhui Deng, Arturo Argueta, Tresi Arvizo, Roger Hsiao, Sasha Kuznietsov, Yiu-Chang Lin, Xiaoqiang Xiao, Yuanyuan Zhang

Figure 1 for Cross-lingual Knowledge Transfer and Iterative Pseudo-labeling for Low-Resource Speech Recognition with Transducers
Figure 2 for Cross-lingual Knowledge Transfer and Iterative Pseudo-labeling for Low-Resource Speech Recognition with Transducers
Figure 3 for Cross-lingual Knowledge Transfer and Iterative Pseudo-labeling for Low-Resource Speech Recognition with Transducers
Figure 4 for Cross-lingual Knowledge Transfer and Iterative Pseudo-labeling for Low-Resource Speech Recognition with Transducers
Viaarxiv icon

AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation

May 19, 2023
Sara Papi, Marco Turchi, Matteo Negri

Figure 1 for AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation
Figure 2 for AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation
Figure 3 for AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation
Figure 4 for AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation
Viaarxiv icon

Speech Enhancement for Virtual Meetings on Cellular Networks

Feb 16, 2023
Hojeong Lee, Minseon Gwak, Kawon Lee, Minjeong Kim, Joseph Konan, Ojas Bhargave

Figure 1 for Speech Enhancement for Virtual Meetings on Cellular Networks
Figure 2 for Speech Enhancement for Virtual Meetings on Cellular Networks
Figure 3 for Speech Enhancement for Virtual Meetings on Cellular Networks
Figure 4 for Speech Enhancement for Virtual Meetings on Cellular Networks
Viaarxiv icon

Automatic Identification of Alzheimer's Disease using Lexical Features extracted from Language Samples

Jul 16, 2023
M. Zakaria Kurdi

Figure 1 for Automatic Identification of Alzheimer's Disease using Lexical Features extracted from Language Samples
Figure 2 for Automatic Identification of Alzheimer's Disease using Lexical Features extracted from Language Samples
Figure 3 for Automatic Identification of Alzheimer's Disease using Lexical Features extracted from Language Samples
Figure 4 for Automatic Identification of Alzheimer's Disease using Lexical Features extracted from Language Samples
Viaarxiv icon

Speech Privacy Leakage from Shared Gradients in Distributed Learning

Feb 21, 2023
Zhuohang Li, Jiaxin Zhang, Jian Liu

Figure 1 for Speech Privacy Leakage from Shared Gradients in Distributed Learning
Figure 2 for Speech Privacy Leakage from Shared Gradients in Distributed Learning
Figure 3 for Speech Privacy Leakage from Shared Gradients in Distributed Learning
Figure 4 for Speech Privacy Leakage from Shared Gradients in Distributed Learning
Viaarxiv icon

Mitigating Label Bias via Decoupled Confident Learning

Jul 18, 2023
Yunyi Li, Maria De-Arteaga, Maytal Saar-Tsechansky

Figure 1 for Mitigating Label Bias via Decoupled Confident Learning
Figure 2 for Mitigating Label Bias via Decoupled Confident Learning
Figure 3 for Mitigating Label Bias via Decoupled Confident Learning
Figure 4 for Mitigating Label Bias via Decoupled Confident Learning
Viaarxiv icon

VoxWatch: An open-set speaker recognition benchmark on VoxCeleb

Jun 30, 2023
Raghuveer Peri, Seyed Omid Sadjadi, Daniel Garcia-Romero

Figure 1 for VoxWatch: An open-set speaker recognition benchmark on VoxCeleb
Figure 2 for VoxWatch: An open-set speaker recognition benchmark on VoxCeleb
Figure 3 for VoxWatch: An open-set speaker recognition benchmark on VoxCeleb
Figure 4 for VoxWatch: An open-set speaker recognition benchmark on VoxCeleb
Viaarxiv icon

Speaker-Independent Acoustic-to-Articulatory Speech Inversion

Feb 14, 2023
Peter Wu, Li-Wei Chen, Cheol Jun Cho, Shinji Watanabe, Louis Goldstein, Alan W Black, Gopala K. Anumanchipalli

Figure 1 for Speaker-Independent Acoustic-to-Articulatory Speech Inversion
Figure 2 for Speaker-Independent Acoustic-to-Articulatory Speech Inversion
Figure 3 for Speaker-Independent Acoustic-to-Articulatory Speech Inversion
Figure 4 for Speaker-Independent Acoustic-to-Articulatory Speech Inversion
Viaarxiv icon