Alert button

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

DHASP: Differentiable Hearing Aid Speech Processing

Mar 15, 2021
Zehai Tu, Ning Ma, Jon Barker

Figure 1 for DHASP: Differentiable Hearing Aid Speech Processing
Figure 2 for DHASP: Differentiable Hearing Aid Speech Processing
Figure 3 for DHASP: Differentiable Hearing Aid Speech Processing
Figure 4 for DHASP: Differentiable Hearing Aid Speech Processing
Viaarxiv icon

Detecting Hate Speech with GPT-3

Mar 23, 2021
Ke-Li Chiu, Rohan Alexander

Figure 1 for Detecting Hate Speech with GPT-3
Figure 2 for Detecting Hate Speech with GPT-3
Figure 3 for Detecting Hate Speech with GPT-3
Figure 4 for Detecting Hate Speech with GPT-3
Viaarxiv icon

Adversarial and Safely Scaled Question Generation

Oct 17, 2022
Sreehari Sankar, Zhihang Dong

Figure 1 for Adversarial and Safely Scaled Question Generation
Figure 2 for Adversarial and Safely Scaled Question Generation
Figure 3 for Adversarial and Safely Scaled Question Generation
Figure 4 for Adversarial and Safely Scaled Question Generation
Viaarxiv icon

Continuous Pseudo-Labeling from the Start

Oct 17, 2022
Dan Berrebbi, Ronan Collobert, Samy Bengio, Navdeep Jaitly, Tatiana Likhomanenko

Figure 1 for Continuous Pseudo-Labeling from the Start
Figure 2 for Continuous Pseudo-Labeling from the Start
Figure 3 for Continuous Pseudo-Labeling from the Start
Figure 4 for Continuous Pseudo-Labeling from the Start
Viaarxiv icon

Time-domain Speech Enhancement with Generative Adversarial Learning

Mar 30, 2021
Feiyang Xiao, Jian Guan, Qiuqiang Kong, Wenwu Wang

Figure 1 for Time-domain Speech Enhancement with Generative Adversarial Learning
Figure 2 for Time-domain Speech Enhancement with Generative Adversarial Learning
Viaarxiv icon

Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer

Jul 29, 2022
Cong-Thanh Do, Mohan Li, Rama Doddipatla

Figure 1 for Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer
Figure 2 for Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer
Figure 3 for Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer
Figure 4 for Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer
Viaarxiv icon

Weakly-supervised word-level pronunciation error detection in non-native English speech

Jun 07, 2021
Daniel Korzekwa, Jaime Lorenzo-Trueba, Thomas Drugman, Shira Calamaro, Bozena Kostek

Figure 1 for Weakly-supervised word-level pronunciation error detection in non-native English speech
Figure 2 for Weakly-supervised word-level pronunciation error detection in non-native English speech
Figure 3 for Weakly-supervised word-level pronunciation error detection in non-native English speech
Figure 4 for Weakly-supervised word-level pronunciation error detection in non-native English speech
Viaarxiv icon

Lexical Access Model for Italian -- Modeling human speech processing: identification of words in running speech toward lexical access based on the detection of landmarks and other acoustic cues to features

Jun 24, 2021
Maria-Gabriella Di Benedetto, Stefanie Shattuck-Hufnagel, Jeung-Yoon Choi, Luca De Nardis, Javier Arango, Ian Chan, Alec DeCaprio

Figure 1 for Lexical Access Model for Italian -- Modeling human speech processing: identification of words in running speech toward lexical access based on the detection of landmarks and other acoustic cues to features
Figure 2 for Lexical Access Model for Italian -- Modeling human speech processing: identification of words in running speech toward lexical access based on the detection of landmarks and other acoustic cues to features
Figure 3 for Lexical Access Model for Italian -- Modeling human speech processing: identification of words in running speech toward lexical access based on the detection of landmarks and other acoustic cues to features
Figure 4 for Lexical Access Model for Italian -- Modeling human speech processing: identification of words in running speech toward lexical access based on the detection of landmarks and other acoustic cues to features
Viaarxiv icon

Continuous Speech Separation with Ad Hoc Microphone Arrays

Mar 03, 2021
Dongmei Wang, Takuya Yoshioka, Zhuo Chen, Xiaofei Wang, Tianyan Zhou, Zhong Meng

Figure 1 for Continuous Speech Separation with Ad Hoc Microphone Arrays
Figure 2 for Continuous Speech Separation with Ad Hoc Microphone Arrays
Figure 3 for Continuous Speech Separation with Ad Hoc Microphone Arrays
Figure 4 for Continuous Speech Separation with Ad Hoc Microphone Arrays
Viaarxiv icon

Cross-speaker style transfer for text-to-speech using data augmentation

Feb 10, 2022
Manuel Sam Ribeiro, Julian Roth, Giulia Comini, Goeric Huybrechts, Adam Gabrys, Jaime Lorenzo-Trueba

Figure 1 for Cross-speaker style transfer for text-to-speech using data augmentation
Figure 2 for Cross-speaker style transfer for text-to-speech using data augmentation
Figure 3 for Cross-speaker style transfer for text-to-speech using data augmentation
Figure 4 for Cross-speaker style transfer for text-to-speech using data augmentation
Viaarxiv icon