UB Paderborn / Katalog / Suche / in CDI

Preventing Early Endpointing for Online Automatic Speech Recognition

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, p.6813-6817

2021

Volltextzugriff (PDF)

Modification on LSA speech enhancement for speech recognition

2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017, p.5475-5479

2017

Volltextzugriff (PDF)

Efficient methods to train multilingual bottleneck feature extractors for low resource keyword search

2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017, p.5650-5654

2017

Volltextzugriff (PDF)

Unsupervised data selection and word-morph mixed language model for tamil low-resource keyword search

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015, p.4714-4718

2015

Volltextzugriff (PDF)

From English pitch accent detection to Mandarin stress detection, where is the difference?

Computer speech & language, 2012-06, Vol.26 (3), p.127-148

2012

Volltextzugriff (PDF)

A keyword-aware grammar framework for LVCSR-based spoken keyword search

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015, p.5196-5200

2015

Volltextzugriff (PDF)

Cross-lingual deep neural network based submodular unbiased data selection for low-resource keyword search

2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016, p.6015-6019

2016

Volltextzugriff (PDF)

Submodular data selection with acoustic and phonetic features for automatic speech recognition

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015, p.4629-4633

2015

Volltextzugriff (PDF)

Submodular Based Unsupervised Data Selection

IEICE Transactions on Information and Systems, 2018/06/01, Vol.E101.D(6), pp.1591-1604

2018

Volltextzugriff (PDF)

De'hubert: Disentangling Noise in a Self-Supervised Model for Robust Speech Recognition

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

2023

Volltextzugriff (PDF)

Long short-term memory recurrent neural network based segment features for music genre classification

2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP), 2016, p.1-5

2016

Volltextzugriff (PDF)

Contrastive Speech Mixup for Low-Resource Keyword Spotting

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

2023

Volltextzugriff (PDF)

MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, p.10356-10360

2024

Volltextzugriff (PDF)

SPGM: Prioritizing Local Features for Enhanced Speech Separation Performance

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, p.326-330

2024

Volltextzugriff (PDF)

Are Soft Prompts Good Zero-Shot Learners for Speech Recognition?

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, p.10366-10370

2024

Volltextzugriff (PDF)

Investigate automatic speech recognition and keyword search for very low-resource language

2017 IEEE 2nd International Conference on Signal and Image Processing (ICSIP), 2017, p.336-340

2017

Volltextzugriff (PDF)

Independent Language Modeling Architecture for End-To-End ASR

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, p.7059-7063

2020

Volltextzugriff (PDF)

Investigation of using different Chinese word segmentation standards and algorithms for automatic speech recognition

The 9th International Symposium on Chinese Spoken Language Processing, 2014, p.44-48

2014

Volltextzugriff (PDF)

Semi-supervised Learning of Bottleneck Feature for Music Genre Classification

Pattern Recognition, p.552-562

Volltextzugriff (PDF)

A novel codebook representation method and encoding strategy for bag-of-words based acoustic event classification

2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2015, p.31-34

2015

Volltextzugriff (PDF)

A novel keyword+LVCSR-filler based grammar network representation for spoken keyword search

The 9th International Symposium on Chinese Spoken Language Processing, 2014, p.192-196

2014

Volltextzugriff (PDF)

A Keyword-Aware Language Modeling Approach to Spoken Keyword Search

Journal of signal processing systems, 2016-02, Vol.82 (2), p.197-206

2016

Volltextzugriff (PDF)

Multiple time-span feature fusion for deep neural network modeling

The 9th International Symposium on Chinese Spoken Language Processing, 2014, p.138-142

2014

Volltextzugriff (PDF)

Low-resource keyword search strategies for tamil

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015, p.5366-5370

2015

Volltextzugriff (PDF)

Exemplar-inspired strategies for low-resource spoken keyword search in Swahili

2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016, p.6040-6044

2016

Volltextzugriff (PDF)

Menü

Weitere Dienste

Einstellungen

Preventing Early Endpointing for Online Automatic Speech Recognition

Modification on LSA speech enhancement for speech recognition

Efficient methods to train multilingual bottleneck feature extractors for low resource keyword search

Unsupervised data selection and word-morph mixed language model for tamil low-resource keyword search

From English pitch accent detection to Mandarin stress detection, where is the difference?

A keyword-aware grammar framework for LVCSR-based spoken keyword search

Cross-lingual deep neural network based submodular unbiased data selection for low-resource keyword search

Submodular data selection with acoustic and phonetic features for automatic speech recognition

Submodular Based Unsupervised Data Selection

De'hubert: Disentangling Noise in a Self-Supervised Model for Robust Speech Recognition

Long short-term memory recurrent neural network based segment features for music genre classification

Contrastive Speech Mixup for Low-Resource Keyword Spotting

MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation

SPGM: Prioritizing Local Features for Enhanced Speech Separation Performance

Are Soft Prompts Good Zero-Shot Learners for Speech Recognition?

Investigate automatic speech recognition and keyword search for very low-resource language

Independent Language Modeling Architecture for End-To-End ASR

Investigation of using different Chinese word segmentation standards and algorithms for automatic speech recognition

Semi-supervised Learning of Bottleneck Feature for Music Genre Classification

A novel codebook representation method and encoding strategy for bag-of-words based acoustic event classification

A novel keyword+LVCSR-filler based grammar network representation for spoken keyword search

A Keyword-Aware Language Modeling Approach to Spoken Keyword Search

Multiple time-span feature fusion for deep neural network modeling

Low-resource keyword search strategies for tamil

Exemplar-inspired strategies for low-resource spoken keyword search in Swahili

Suchergebnisse filtern