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 …
into Air Traffic Control (ATC), where spoken language is still the predominant form of …
[PDF][PDF] Iterative Learning of Speech Recognition Models for Air Traffic Control.
Abstract Automatic Speech Recognition (ASR) has recently proved to be a useful tool to
reduce the workload of air traffic controllers leading to significant gains in operational …
reduce the workload of air traffic controllers leading to significant gains in operational …
Language model adaptation based on filtered data
R Bretter, S Artzi, M Nissan - US Patent 9,564,122, 2017 - Google Patents
BACKGROUND The present disclosure generally relates to textual terms recognition, and
more specifically to speech recognition using a language model adapted with external data …
more specifically to speech recognition using a language model adapted with external data …
[PDF][PDF] Simple gesture-based error correction interface for smartphone speech recognition.
Conventional error correction interfaces for speech recognition require a user to first mark an
error region and choose the correct word from a candidate list. Taking the user's effort and …
error region and choose the correct word from a candidate list. Taking the user's effort and …
[PDF][PDF] Unsupervised language model adaptation for automatic speech recognition of broadcast news using web 2.0.
We improve the automatic speech recognition of broadcast news using paradigms from Web
2.0 to obtain time-and topicrelevant text data for language modeling. We elaborate an …
2.0 to obtain time-and topicrelevant text data for language modeling. We elaborate an …
[PDF][PDF] Combinations of various language model technologies including data expansion and adaptation in spontaneous speech recognition.
This paper demonstrates combinations of various language model (LM) technologies
simultaneously, not only modeling techniques but also those for training data expansion …
simultaneously, not only modeling techniques but also those for training data expansion …
Focusing language models for automatic speech recognition
DFR Gretter - Proceedings of the 9th International Workshop on …, 2012 - aclanthology.org
This paper describes a method for selecting text data from a corpus with the aim of training
auxiliary Language Models (LMs) for an Automatic Speech Recognition (ASR) system. A …
auxiliary Language Models (LMs) for an Automatic Speech Recognition (ASR) system. A …
A preliminary study on topical model for multi-domain speech recognition via word embedding vector
J Moon, S Yun, D Lee, S Kim - 2019 34th International …, 2019 - ieeexplore.ieee.org
In this paper, we suggest a basic topical model (TM) framework to adapt speech recognition
system to multi-domain and prevent topical errors. This paper employs the cosine similarities …
system to multi-domain and prevent topical errors. This paper employs the cosine similarities …
FBK@ IWSLT 2012–ASR track
D Falavigna, R Gretter, F Brugnara… - Proceedings of the 9th …, 2012 - aclanthology.org
This paper reports on the participation of FBK at the IWSLT2012 evaluation campaign on
automatic speech recognition: namely in the English ASR track. Both primary and …
automatic speech recognition: namely in the English ASR track. Both primary and …
Training RNN language models on uncertain ASR hypotheses in limited data scenarios
Training domain-specific automatic speech recognition (ASR) systems requires a suitable
amount of data comprising the target domain. In several scenarios, such as early …
amount of data comprising the target domain. In several scenarios, such as early …