Alert button

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

Laughter Synthesis using Pseudo Phonetic Tokens with a Large-scale In-the-wild Laughter Corpus

May 26, 2023
Detai Xin, Shinnosuke Takamichi, Ai Morimatsu, Hiroshi Saruwatari

Figure 1 for Laughter Synthesis using Pseudo Phonetic Tokens with a Large-scale In-the-wild Laughter Corpus
Figure 2 for Laughter Synthesis using Pseudo Phonetic Tokens with a Large-scale In-the-wild Laughter Corpus
Figure 3 for Laughter Synthesis using Pseudo Phonetic Tokens with a Large-scale In-the-wild Laughter Corpus
Figure 4 for Laughter Synthesis using Pseudo Phonetic Tokens with a Large-scale In-the-wild Laughter Corpus
Viaarxiv icon

Leveraging characteristics of the output probability distribution for identifying adversarial audio examples

May 26, 2023
Matías P. Pizarro B., Dorothea Kolossa, Asja Fischer

Figure 1 for Leveraging characteristics of the output probability distribution for identifying adversarial audio examples
Figure 2 for Leveraging characteristics of the output probability distribution for identifying adversarial audio examples
Figure 3 for Leveraging characteristics of the output probability distribution for identifying adversarial audio examples
Figure 4 for Leveraging characteristics of the output probability distribution for identifying adversarial audio examples
Viaarxiv icon

Understanding temporally weakly supervised training: A case study for keyword spotting

May 30, 2023
Heinrich Dinkel, Weiji Zhuang, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Yujun Wang

Figure 1 for Understanding temporally weakly supervised training: A case study for keyword spotting
Figure 2 for Understanding temporally weakly supervised training: A case study for keyword spotting
Figure 3 for Understanding temporally weakly supervised training: A case study for keyword spotting
Figure 4 for Understanding temporally weakly supervised training: A case study for keyword spotting
Viaarxiv icon

Self-supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces

May 21, 2023
Oli Liu, Hao Tang, Sharon Goldwater

Figure 1 for Self-supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces
Figure 2 for Self-supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces
Figure 3 for Self-supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces
Figure 4 for Self-supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces
Viaarxiv icon

Spoofing Attacker Also Benefits from Self-Supervised Pretrained Model

May 24, 2023
Aoi Ito, Shota Horiguchi

Figure 1 for Spoofing Attacker Also Benefits from Self-Supervised Pretrained Model
Figure 2 for Spoofing Attacker Also Benefits from Self-Supervised Pretrained Model
Figure 3 for Spoofing Attacker Also Benefits from Self-Supervised Pretrained Model
Figure 4 for Spoofing Attacker Also Benefits from Self-Supervised Pretrained Model
Viaarxiv icon

Leveraging Redundancy in Multiple Audio Signals for Far-Field Speech Recognition

Mar 01, 2023
Feng-Ju Chang, Anastasios Alexandridis, Rupak Vignesh Swaminathan, Martin Radfar, Harish Mallidi, Maurizio Omologo, Athanasios Mouchtaris, Brian King, Roland Maas

Figure 1 for Leveraging Redundancy in Multiple Audio Signals for Far-Field Speech Recognition
Figure 2 for Leveraging Redundancy in Multiple Audio Signals for Far-Field Speech Recognition
Figure 3 for Leveraging Redundancy in Multiple Audio Signals for Far-Field Speech Recognition
Figure 4 for Leveraging Redundancy in Multiple Audio Signals for Far-Field Speech Recognition
Viaarxiv icon

Exploring Effective Fusion Algorithms for Speech Based Self-Supervised Learning Models

Dec 20, 2022
Changli Tang, Yujin Wang, Xie Chen, Wei-Qiang Zhang

Figure 1 for Exploring Effective Fusion Algorithms for Speech Based Self-Supervised Learning Models
Figure 2 for Exploring Effective Fusion Algorithms for Speech Based Self-Supervised Learning Models
Figure 3 for Exploring Effective Fusion Algorithms for Speech Based Self-Supervised Learning Models
Figure 4 for Exploring Effective Fusion Algorithms for Speech Based Self-Supervised Learning Models
Viaarxiv icon

DDSupport: Language Learning Support System that Displays Differences and Distances from Model Speech

Dec 08, 2022
Kazuki Kawamura, Jun Rekimoto

Figure 1 for DDSupport: Language Learning Support System that Displays Differences and Distances from Model Speech
Figure 2 for DDSupport: Language Learning Support System that Displays Differences and Distances from Model Speech
Figure 3 for DDSupport: Language Learning Support System that Displays Differences and Distances from Model Speech
Figure 4 for DDSupport: Language Learning Support System that Displays Differences and Distances from Model Speech
Viaarxiv icon

Joint unsupervised and supervised learning for context-aware language identification

Apr 14, 2023
Jinseok Park, Hyung Yong Kim, Jihwan Park, Byeong-Yeol Kim, Shukjae Choi, Yunkyu Lim

Figure 1 for Joint unsupervised and supervised learning for context-aware language identification
Figure 2 for Joint unsupervised and supervised learning for context-aware language identification
Figure 3 for Joint unsupervised and supervised learning for context-aware language identification
Figure 4 for Joint unsupervised and supervised learning for context-aware language identification
Viaarxiv icon

Exploring Speaker-Related Information in Spoken Language Understanding for Better Speaker Diarization

May 22, 2023
Luyao Cheng, Siqi Zheng, Zhang Qinglin, Hui Wang, Yafeng Chen, Qian Chen

Figure 1 for Exploring Speaker-Related Information in Spoken Language Understanding for Better Speaker Diarization
Figure 2 for Exploring Speaker-Related Information in Spoken Language Understanding for Better Speaker Diarization
Figure 3 for Exploring Speaker-Related Information in Spoken Language Understanding for Better Speaker Diarization
Figure 4 for Exploring Speaker-Related Information in Spoken Language Understanding for Better Speaker Diarization
Viaarxiv icon