Alert button
Picture for John H. L. Hansen

John H. L. Hansen

Alert button

Efficient Adapter Tuning of Pre-trained Speech Models for Automatic Speaker Verification

Mar 01, 2024
Mufan Sang, John H. L. Hansen

Figure 1 for Efficient Adapter Tuning of Pre-trained Speech Models for Automatic Speaker Verification
Figure 2 for Efficient Adapter Tuning of Pre-trained Speech Models for Automatic Speaker Verification
Figure 3 for Efficient Adapter Tuning of Pre-trained Speech Models for Automatic Speaker Verification
Figure 4 for Efficient Adapter Tuning of Pre-trained Speech Models for Automatic Speaker Verification
Viaarxiv icon

Multi-objective Non-intrusive Hearing-aid Speech Assessment Model

Nov 15, 2023
Hsin-Tien Chiang, Szu-Wei Fu, Hsin-Min Wang, Yu Tsao, John H. L. Hansen

Figure 1 for Multi-objective Non-intrusive Hearing-aid Speech Assessment Model
Figure 2 for Multi-objective Non-intrusive Hearing-aid Speech Assessment Model
Figure 3 for Multi-objective Non-intrusive Hearing-aid Speech Assessment Model
Figure 4 for Multi-objective Non-intrusive Hearing-aid Speech Assessment Model
Viaarxiv icon

MixRep: Hidden Representation Mixup for Low-Resource Speech Recognition

Oct 27, 2023
Jiamin Xie, John H. L. Hansen

Viaarxiv icon

Advanced accent/dialect identification and accentedness assessment with multi-embedding models and automatic speech recognition

Oct 17, 2023
Shahram Ghorbani, John H. L. Hansen

Viaarxiv icon

What Can an Accent Identifier Learn? Probing Phonetic and Prosodic Information in a Wav2vec2-based Accent Identification Model

Jun 10, 2023
Mu Yang, Ram C. M. C. Shekar, Okim Kang, John H. L. Hansen

Figure 1 for What Can an Accent Identifier Learn? Probing Phonetic and Prosodic Information in a Wav2vec2-based Accent Identification Model
Figure 2 for What Can an Accent Identifier Learn? Probing Phonetic and Prosodic Information in a Wav2vec2-based Accent Identification Model
Figure 3 for What Can an Accent Identifier Learn? Probing Phonetic and Prosodic Information in a Wav2vec2-based Accent Identification Model
Figure 4 for What Can an Accent Identifier Learn? Probing Phonetic and Prosodic Information in a Wav2vec2-based Accent Identification Model
Viaarxiv icon

Improving Transformer-based Networks With Locality For Automatic Speaker Verification

Feb 28, 2023
Mufan Sang, Yong Zhao, Gang Liu, John H. L. Hansen, Jian Wu

Figure 1 for Improving Transformer-based Networks With Locality For Automatic Speaker Verification
Figure 2 for Improving Transformer-based Networks With Locality For Automatic Speaker Verification
Figure 3 for Improving Transformer-based Networks With Locality For Automatic Speaker Verification
Figure 4 for Improving Transformer-based Networks With Locality For Automatic Speaker Verification
Viaarxiv icon

Complex-Valued Time-Frequency Self-Attention for Speech Dereverberation

Nov 22, 2022
Vinay Kothapally, John H. L. Hansen

Figure 1 for Complex-Valued Time-Frequency Self-Attention for Speech Dereverberation
Figure 2 for Complex-Valued Time-Frequency Self-Attention for Speech Dereverberation
Figure 3 for Complex-Valued Time-Frequency Self-Attention for Speech Dereverberation
Figure 4 for Complex-Valued Time-Frequency Self-Attention for Speech Dereverberation
Viaarxiv icon

Filterbank Learning for Small-Footprint Keyword Spotting Robust to Noise

Nov 19, 2022
Iván López-Espejo, Ram C. M. C. Shekar, Zheng-Hua Tan, Jesper Jensen, John H. L. Hansen

Figure 1 for Filterbank Learning for Small-Footprint Keyword Spotting Robust to Noise
Figure 2 for Filterbank Learning for Small-Footprint Keyword Spotting Robust to Noise
Figure 3 for Filterbank Learning for Small-Footprint Keyword Spotting Robust to Noise
Figure 4 for Filterbank Learning for Small-Footprint Keyword Spotting Robust to Noise
Viaarxiv icon

Multi-source Domain Adaptation for Text-independent Forensic Speaker Recognition

Nov 17, 2022
Zhenyu Wang, John H. L. Hansen

Figure 1 for Multi-source Domain Adaptation for Text-independent Forensic Speaker Recognition
Figure 2 for Multi-source Domain Adaptation for Text-independent Forensic Speaker Recognition
Figure 3 for Multi-source Domain Adaptation for Text-independent Forensic Speaker Recognition
Figure 4 for Multi-source Domain Adaptation for Text-independent Forensic Speaker Recognition
Viaarxiv icon