UB Paderborn / Katalog / Suche / in CDI

Emotion Recognition by Fusing Time Synchronous and Time Asynchronous Representations

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, p.6269-6273

2021

Volltextzugriff (PDF)

Unsupervised training and directed manual transcription for LVCSR

Speech communication, 2010-07, Vol.52 (7), p.652-663

2010

Volltextzugriff (PDF)

Combination of deep speaker embeddings for diarisation

Neural networks, 2021-09, Vol.141, p.372-384

2021

Volltextzugriff (PDF)

Syllable language models for Mandarin speech recognition: exploiting character language models

The Journal of the Acoustical Society of America, 2013-01, Vol.133 (1), p.519-528

2013

Volltextzugriff (PDF)

A distributed optimisation framework combining natural gradient with Hessian-free for discriminative sequence training

Neural networks, 2021-11, Vol.143, p.537-549

2021

Volltextzugriff (PDF)

Knowledge Distillation for Neural Transducers from Large Self-Supervised Pre-Trained Models

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, p.8527-8531

2022

Volltextzugriff (PDF)

Confidence Estimation for Attention-Based Sequence-to-Sequence Models for Speech Recognition

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, p.6388-6392

2021

Volltextzugriff (PDF)

Estimating the Uncertainty in Emotion Class Labels With Utterance-Specific Dirichlet Priors

IEEE transactions on affective computing, 2023-10, Vol.14 (4), p.1-13

2023

Volltextzugriff (PDF)

Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, p.6537-6541

2022

Volltextzugriff (PDF)

MPE-based discriminative linear transforms for speaker adaptation

Computer speech & language, 2008-07, Vol.22 (3), p.256-272

2008

Volltextzugriff (PDF)

Efficient Training and Evaluation of Recurrent Neural Network Language Models for Automatic Speech Recognition

IEEE/ACM transactions on audio, speech, and language processing, 2016-11, Vol.24 (11), p.2146-2157

2016

Volltextzugriff (PDF)

Two Efficient Lattice Rescoring Methods Using Recurrent Neural Network Language Models

IEEE/ACM transactions on audio, speech, and language processing, 2016-08, Vol.24 (8), p.1438-1449

2016

Volltextzugriff (PDF)

Decoupled structure for improved adaptability of end-to-end models

Speech communication, 2024-09, Vol.163, p.103109, Article 103109

2024

Volltextzugriff (PDF)

I-Vectors and Structured Neural Networks for Rapid Adaptation of Acoustic Models

IEEE/ACM transactions on audio, speech, and language processing, 2017-04, Vol.25 (4), p.818-828

2017

Volltextzugriff (PDF)

Tree-Constrained Pointer Generator for End-to-End Contextual Speech Recognition

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2021, p.780-787

2021

Volltextzugriff (PDF)

A computational model of the auditory periphery for speech and hearing research. I. Ascending path

The Journal of the Acoustical Society of America, 1994-01, Vol.95 (1), p.331

1994

Volltextzugriff (PDF)

Unsupervised Adaptation With Discriminative Mapping Transforms

IEEE transactions on audio, speech, and language processing, 2009-05, Vol.17 (4), p.714-723

2009

Volltextzugriff (PDF)

Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2021, p.162-168

2021

Volltextzugriff (PDF)

Combining hybrid DNN-HMM ASR systems with attention-based models using lattice rescoring

Speech communication, 2023-02, Vol.147, p.12-21

2023

Volltextzugriff (PDF)

Label-Synchronous Neural Transducer for Adaptable Online E2E Speech Recognition

IEEE/ACM transactions on audio, speech, and language processing, 2024, Vol.32, p.3507-3516

2024

Volltextzugriff (PDF)

FastInject: Injecting Unpaired Text Data into CTC-Based ASR Training

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, p.11836-11840

2024

Volltextzugriff (PDF)

Adaptable End-to-End ASR Models Using Replaceable Internal LMs and Residual Softmax

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023, p.1-5

2023

Volltextzugriff (PDF)

Integrating Source-Channel and Attention-Based Sequence-to-Sequence Models for Speech Recognition

2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2019, p.39-46

2019

Volltextzugriff (PDF)

Graph Neural Networks for Contextual ASR With the Tree-Constrained Pointer Generator

IEEE/ACM transactions on audio, speech, and language processing, 2024, Vol.32, p.2407-2417

2024

Volltextzugriff (PDF)

End-to-End Spoken Language Understanding with Tree-Constrained Pointer Generator

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023, p.1-5

2023

Volltextzugriff (PDF)

Menü

Weitere Dienste

Einstellungen

Emotion Recognition by Fusing Time Synchronous and Time Asynchronous Representations

Unsupervised training and directed manual transcription for LVCSR

Combination of deep speaker embeddings for diarisation

Syllable language models for Mandarin speech recognition: exploiting character language models

A distributed optimisation framework combining natural gradient with Hessian-free for discriminative sequence training

Knowledge Distillation for Neural Transducers from Large Self-Supervised Pre-Trained Models

Confidence Estimation for Attention-Based Sequence-to-Sequence Models for Speech Recognition

Estimating the Uncertainty in Emotion Class Labels With Utterance-Specific Dirichlet Priors

Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition

MPE-based discriminative linear transforms for speaker adaptation

Efficient Training and Evaluation of Recurrent Neural Network Language Models for Automatic Speech Recognition

Two Efficient Lattice Rescoring Methods Using Recurrent Neural Network Language Models

Decoupled structure for improved adaptability of end-to-end models

I-Vectors and Structured Neural Networks for Rapid Adaptation of Acoustic Models

Tree-Constrained Pointer Generator for End-to-End Contextual Speech Recognition

A computational model of the auditory periphery for speech and hearing research. I. Ascending path

Unsupervised Adaptation With Discriminative Mapping Transforms

Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition

Combining hybrid DNN-HMM ASR systems with attention-based models using lattice rescoring

Label-Synchronous Neural Transducer for Adaptable Online E2E Speech Recognition

FastInject: Injecting Unpaired Text Data into CTC-Based ASR Training

Adaptable End-to-End ASR Models Using Replaceable Internal LMs and Residual Softmax

Integrating Source-Channel and Attention-Based Sequence-to-Sequence Models for Speech Recognition

Graph Neural Networks for Contextual ASR With the Tree-Constrained Pointer Generator

End-to-End Spoken Language Understanding with Tree-Constrained Pointer Generator

Suchergebnisse filtern