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)

Deep Learning for Audio Signal Processing

IEEE journal of selected topics in signal processing, 2019-05, Vol.13 (2), p.206-219

2019

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)

A Better and Faster end-to-end Model for Streaming ASR

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, p.5634-5638

2021

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)

On the importance of modeling and robustness for deep neural network feature

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015, p.4530-4534

2015

Volltextzugriff (PDF)

Spectro-temporal features for noise-robust speech recognition using power-law nonlinearity and power-bias subtraction

2013 IEEE International Conference on Acoustics, Speech and Signal Processing, 2013, p.7063-7067

2013

Volltextzugriff (PDF)

Improving the Fusion of Acoustic and Text Representations in RNN-T

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, p.8117-8121

2022

Volltextzugriff (PDF)

Context-Aware end-to-end ASR Using Self-Attentive Embedding and Tensor Fusion

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)

UML: A Universal Monolingual Output Layer For Multilingual Asr

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

2023

Volltextzugriff (PDF)

Temporal Modeling Using Dilated Convolution and Gating for Voice-Activity-Detection

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018, p.5549-5553

2018

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)

The blame game in meeting room ASR: An analysis of feature versus model errors in noisy and mismatched conditions

2013 IEEE International Conference on Acoustics, Speech and Signal Processing, 2013, p.6758-6762

2013

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)

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)

Improved clustered hierarchical tandem system with bottom-up processing

2009 IEEE International Conference on Acoustics, Speech and Signal Processing, 2009, p.4441-4444

2009

Volltextzugriff (PDF)

Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems

2022 IEEE Spoken Language Technology Workshop (SLT), 2023, p.310-316

2023

Volltextzugriff (PDF)

A Unified Endpointer Using Multitask and Multidomain Training

2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2019, p.100-106

2019

Volltextzugriff (PDF)

Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, p.13306-13310

2024

Volltextzugriff (PDF)

Feature Design for Robust Speech Recognition: Nurture and Nature

Chang, Shuo-Yiin

2016

Volltextzugriff (PDF)

1 – 22 von 22

Suche als RSS-Feed

Suchergebnisse filtern

Filter anzeigen

Nur zeigen

Geprüft (Peer-Review)
(1)
Mit Volltextzugriff
(19)

Publikationsform

Sprache

Englisch
(22)

Erscheinungsjahr

n.n

Thema

Acoustics
(18)
Science & Technology
(16)
Technology
(16)
Engineering
(14)
Engineering, Electrical & Electronic
(14)
Signal Processing
(12)
Speech Recognition
(11)
Training
(11)
Automatic Speech Recognition
(7)
Computer Science
(7)
Transducers
(7)
Computer Science, Artificial Intelligence
(6)
Neural Networks
(6)
Coders
(5)
Computational Modeling
(5)
Error Analysis
(5)
Predictive Models
(5)
Decoding
(4)
Error Reduction
(4)
Hidden Markov Models
(4)

15 weitere anzeigen...

Weniger anzeigen...

Kollektion

Zeitschrift / Serie

Ieee Journal Of Selected Topics In Signal Processing
(1)

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

Deep Learning for Audio Signal Processing

Streaming End-to-end Speech Recognition for Mobile Devices

A Better and Faster end-to-end Model for Streaming ASR

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

On the importance of modeling and robustness for deep neural network feature

Spectro-temporal features for noise-robust speech recognition using power-law nonlinearity and power-bias subtraction

Improving the Fusion of Acoustic and Text Representations in RNN-T

Context-Aware end-to-end ASR Using Self-Attentive Embedding and Tensor Fusion

Joint Endpointing and Decoding with End-to-end Models

UML: A Universal Monolingual Output Layer For Multilingual Asr

Temporal Modeling Using Dilated Convolution and Gating for Voice-Activity-Detection

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

The blame game in meeting room ASR: An analysis of feature versus model errors in noisy and mismatched conditions

Improving The Latency And Quality Of Cascaded Encoders

E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model

Improved clustered hierarchical tandem system with bottom-up processing

Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems

A Unified Endpointer Using Multitask and Multidomain Training

Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study

Feature Design for Robust Speech Recognition: Nurture and Nature

Suchergebnisse filtern