UB Paderborn / Katalog / Suche / in CDI

Sortiert nach

Einfacher Volltextzugriff von (fast) überall

Installieren Sie die LibKey Nomad-Browsererweiterung und erhalten Sie von vielen Webseiten einfachen Zugriff auf lizenzierte Volltexte oder Open Access Publikationen. Mehr erfahren...

Towards Fast and Accurate Streaming End-To-End ASR

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, p.6069-6073

2020

Volltextzugriff (PDF)

A Streaming On-Device End-To-End Model Surpassing Server-Side Conventional Model Quality and Latency

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, p.6059-6063

2020

Volltextzugriff (PDF)

Subword-based modeling for handling OOV words inkeyword spotting

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2014, p.7864-7868

2014

Volltextzugriff (PDF)

Using Pronunciation-Based Morphological Subword Units to Improve OOV Handling in Keyword Search

IEEE/ACM transactions on audio, speech, and language processing, 2016-01, Vol.24 (1), p.79-92

2016

Volltextzugriff (PDF)

Streaming small-footprint keyword spotting using sequence-to-sequence models

2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2017, p.474-481

2017

Volltextzugriff (PDF)

Streaming End-to-end Speech Recognition for Mobile Devices

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, p.6381-6385

2019

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)

Conditional Random Fields in Speech, Audio, and Language Processing

Proceedings of the IEEE, 2013-05, Vol.101 (5), p.1054-1075

2013

Volltextzugriff (PDF)

FastEmit: Low-Latency Streaming ASR with Sequence-Level Emission Regularization

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, p.6004-6008

2021

Volltextzugriff (PDF)

Large-Scale ASR Domain Adaptation Using Self- and Semi-Supervised Learning

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, p.6627-6631

2022

Volltextzugriff (PDF)

Less is More: Improved RNN-T Decoding Using Limited Label Context and Path Merging

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, p.5659-5663

2021

Volltextzugriff (PDF)

Learning Word-Level Confidence for Subword End-To-End ASR

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, p.6393-6397

2021

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)

Conditional Conformer: Improving Speaker Modulation For Single And Multi-User Speech Enhancement

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

2023

Volltextzugriff (PDF)

Joint Endpointing and Decoding with End-to-end Models

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, p.5626-5630

2019

Volltextzugriff (PDF)

Combining spectral feature mapping and multi-channel model-based source separation for noise-robust automatic speech recognition

2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2015, p.496-503

2015

Volltextzugriff (PDF)

USM-Lite: Quantization and Sparsity Aware Fine-Tuning for Speech Recognition with Universal Speech Models

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, p.10756-10760

2024

Volltextzugriff (PDF)

Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, p.11816-11820

2024

Volltextzugriff (PDF)

Multi-Output RNN-T Joint Networks for Multi-Task Learning of ASR and Auxiliary Tasks

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

2023

Volltextzugriff (PDF)

Improving The Latency And Quality Of Cascaded Encoders

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, p.8112-8116

2022

Volltextzugriff (PDF)

Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition Models

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

2023

Volltextzugriff (PDF)

An Attention-Based Joint Acoustic and Text on-Device End-To-End Model

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, p.7039-7043

2020

Volltextzugriff (PDF)

Self-adaptive Failure Detector for Peer-to-Peer Distributed System Considering the Link Faults

Advanced Parallel Processing Technologies, 2017, Vol.10561, p.64-75

2017

Volltextzugriff (PDF)

E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model

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

2023

Volltextzugriff (PDF)

Conditional Random Fields in Speech, Audio, and Language Processing: SPEECH INFORMATION PROCESSING: THEORY AND APPLICATIONS

Proceedings of the IEEE, 2013, Vol.101 (5), p.1054-1075

2013

Volltextzugriff (PDF)

1 – 25 von 1.035

Suche als RSS-Feed

Aktive Filter

ThemaAnimals

Suchergebnisse filtern

Filter anzeigen

Nur zeigen

Geprüft (Peer-Review)
(810)
Mit Volltextzugriff
(901)

Publikationsform

Sprache

2 weitere anzeigen...

Weniger anzeigen...

Erscheinungsjahr

n.n

Thema

Science & Technology
(691)
Technology
(356)
Physical Sciences
(299)
Engineering
(189)
Life Sciences & Biomedicine
(180)
Physics
(171)
Materials Science
(118)
Engineering, Electrical & Electronic
(116)
Chemistry
(115)
Physics, Applied
(106)
Materials Science, Multidisciplinary
(87)
Computer Science
(78)
Instruments & Instrumentation
(71)
Science & Technology - Other Topics
(68)
Humans
(59)
Chemistry, Multidisciplinary
(52)
Chemistry, Physical
(48)
Computer Science, Artificial Intelligence
(41)
Physics, Condensed Matter
(41)
X-Ray Diffraction
(37)

15 weitere anzeigen...

Weniger anzeigen...

Neu hinzugefügt

... seit 30 Tagen
(8)
... seit 90 Tagen
(26)

Menü

Weitere Dienste

Einstellungen

Towards Fast and Accurate Streaming End-To-End ASR

A Streaming On-Device End-To-End Model Surpassing Server-Side Conventional Model Quality and Latency

Subword-based modeling for handling OOV words inkeyword spotting

Using Pronunciation-Based Morphological Subword Units to Improve OOV Handling in Keyword Search

Streaming small-footprint keyword spotting using sequence-to-sequence models

Streaming End-to-end Speech Recognition for Mobile Devices

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

Conditional Random Fields in Speech, Audio, and Language Processing

FastEmit: Low-Latency Streaming ASR with Sequence-Level Emission Regularization

Large-Scale ASR Domain Adaptation Using Self- and Semi-Supervised Learning

Less is More: Improved RNN-T Decoding Using Limited Label Context and Path Merging

Learning Word-Level Confidence for Subword End-To-End ASR

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

Conditional Conformer: Improving Speaker Modulation For Single And Multi-User Speech Enhancement

Joint Endpointing and Decoding with End-to-end Models

Combining spectral feature mapping and multi-channel model-based source separation for noise-robust automatic speech recognition

USM-Lite: Quantization and Sparsity Aware Fine-Tuning for Speech Recognition with Universal Speech Models

Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models

Multi-Output RNN-T Joint Networks for Multi-Task Learning of ASR and Auxiliary Tasks

Improving The Latency And Quality Of Cascaded Encoders

Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition Models

An Attention-Based Joint Acoustic and Text on-Device End-To-End Model

Self-adaptive Failure Detector for Peer-to-Peer Distributed System Considering the Link Faults

E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model

Conditional Random Fields in Speech, Audio, and Language Processing: SPEECH INFORMATION PROCESSING: THEORY AND APPLICATIONS

Aktive Filter

Suchergebnisse filtern