关注
Tobias Watzel
Tobias Watzel
其他姓名Tobias Dinglreiter
Doctoral Candidate
在 tum.de 的电子邮件经过验证
标题
引用次数
引用次数
年份
Ctc-segmentation of large corpora for german end-to-end speech recognition
L Kürzinger, D Winkelbauer, L Li, T Watzel, G Rigoll
International Conference on Speech and Computer, 267-278, 2020
1102020
Adversarial joint training with self-attention mechanism for robust end-to-end speech recognition
L Li, Y Kang, Y Shi, L Kürzinger, T Watzel, G Rigoll
EURASIP Journal on Audio, Speech, and Music Processing 2021, 1-16, 2021
222021
Light-weight self-attention augmented generative adversarial networks for speech enhancement
L Li, Z Lu, T Watzel, L Kürzinger, G Rigoll
Electronics 10 (13), 1586, 2021
92021
Lightweight End-to-End Speech Enhancement Generative Adversarial Network Using Sinc Convolutions
L Li, Wudamu, L Kuerzinger, T Watzel, G Rigoll
Applied Sciences 11 (16), 7564, 2021
82021
Audio adversarial examples for robust hybrid ctc/attention speech recognition
L Kürzinger, ER Chavez Rosas, L Li, T Watzel, G Rigoll
International Conference on Speech and Computer, 255-266, 2020
52020
Exploring Hybrid CTC/Attention end-to-end speech recognition with gaussian processes
L Kürzinger, T Watzel, L Li, R Baumgartner, G Rigoll
International Conference on Speech and Computer, 258-269, 2019
52019
Deep neural network quantizers outperforming continuous speech recognition systems
T Watzel, L Li, L Kürzinger, G Rigoll
Speech and Computer: 21st International Conference, SPECOM 2019, Istanbul …, 2019
42019
Induced local attention for transformer models in speech recognition
T Watzel, L Kürzinger, L Li, G Rigoll
International Conference on Speech and Computer, 795-806, 2021
32021
Towards Constructing HMM Structure for Speech Recognition With Deep Neural Fenonic Baseform Growing
L Li, T Watzel, L Kuerzinger, G Rigoll
IEEE Access 9, 39098-39110, 2021
32021
Efficient Interaction-Aware Trajectory Prediction Model Based on Multi-head Attention
Z Peng, J Yan, H Yin, Y Wen, W Ge, T Watzel, G Rigoll
Automotive Innovation 7 (2), 258-270, 2024
22024
Regularized forward-backward decoder for attention models
T Watzel, L Kürzinger, L Li, G Rigoll
International Conference on Speech and Computer, 786-794, 2021
22021
Synchronized forward-backward transformer for end-to-end speech recognition
T Watzel, L Kürzinger, L Li, G Rigoll
International Conference on Speech and Computer, 646-656, 2020
12020
Enhancements for Hybrid and End-to-End Speech Recognition Architectures
T Watzel
Technische Universität München, 2023
2023
A Global Discriminant Joint Training Framework for Robust Speech Recognition
L Li, L Kürzinger, T Watzel, G Rigoll
2021 IEEE 33rd International Conference on Tools with Artificial …, 2021
2021
Deep neural fenonic baseform growing: A novel approach to construct HMM topologies for speech recognition
L Li, X Zhou, Z Song, T Watzel, L Kürzinger, G Rigoll
2020 International Conference on High Performance Computing Simulation (HPCS), 2021
2021
Performance Comparison of Deep Neural Network Quantizers to Continuous ASR Systems
T Watzel, G Rigoll
Fortschritte der Akustik--DAGA'19, pp. 947-949, 2019
2019
系统目前无法执行此操作,请稍后再试。
文章 1–16