Semi-supervised learning with semantic knowledge extraction for improved speech recognition in air traffic control

A Srinivasamurthy, P Motlicek… - … of Interspeech 2017, 2017 - infoscience.epfl.ch
Abstract Automatic Speech Recognition (ASR) can introduce higher levels of automation
into Air Traffic Control (ATC), where spoken language is still the predominant form of …

Towards unsupervised learning of speech features in the wild

M Rivière, E Dupoux - 2021 IEEE Spoken Language …, 2021 - ieeexplore.ieee.org
Recent work on unsupervised contrastive learning of speech representation has shown
promising results, but so far has mostly been applied to clean, curated speech datasets. Can …

Semi-supervised adaptation of assistant based speech recognition models for different approach areas

M Kleinert, H Helmke, G Siol, H Ehr… - 2018 IEEE/AIAA 37th …, 2018 - ieeexplore.ieee.org
Air Navigation Service Providers (ANSPs) replace paper flight strips through different digital
solutions. The instructed commands from an air traffic controller (ATCos) are then available …

Semi-supervised acoustic model training for speech with code-switching

E Yılmaz, M McLaren, H van den Heuvel… - Speech …, 2018 - Elsevier
In the FAME! project, we aim to develop an automatic speech recognition (ASR) system for
Frisian-Dutch code-switching (CS) speech extracted from the archives of a local broadcaster …

Semi-supervised ensemble DNN acoustic model training

S Li, X Lu, S Sakai, M Mimura… - 2017 IEEE International …, 2017 - ieeexplore.ieee.org
It is very important to exploit abundant unlabeled speech for improving the acoustic model
training in automatic speech recognition (ASR). Semi-supervised training methods …

Semi-supervised model training for unbounded conversational speech recognition

S Walker, M Pedersen, I Orife, J Flaks - arXiv preprint arXiv:1705.09724, 2017 - arxiv.org
For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to
about two thousand hours of audio is commonly used to train state of the art models …

[HTML][HTML] Acoustic model bootstrapping using semi-supervised learning

L Chen - 2019 - amazon.science
This work aims at bootstrapping the acoustic model training with small amount of the human
annotated speech data and large amount of the unlabelled speech data for automatic …

[HTML][HTML] End-to-end automated speech recognition using a character based small scale transformer architecture

A Loubser, P De Villiers, A De Freitas - Expert Systems with Applications, 2024 - Elsevier
This study explores the feasibility of constructing a small-scale speech recognition system
capable of competing with larger, modern automated speech recognition (ASR) systems in …

In-vehicle voice interface with improved utterance classification accuracy using off-the-shelf cloud speech recognizer

T Homma, Y Obuchi, K Shima, R Ikeshita… - … on Information and …, 2018 - search.ieice.org
For voice-enabled car navigation systems that use a multi-purpose cloud speech recognition
service (cloud ASR), utterance classification that is robust against speech recognition errors …

A progress report of the Taiwan Mandarin radio speech corpus project

YF Liao, YHS Chang, SY Wang… - … 20th Conference of …, 2017 - ieeexplore.ieee.org
The Taiwan Mandarin Radio Speech Corpus contains 300 (and growing) hours of high-
quality recordings selected from Taiwan's National Education Radio (NER) archive. The …