My thesis concerns a study of continuous word representations applied to the automatic detection of speech recognition errors. Our study focuses on the use of a neural approach to improve ASR errors detection, using word embeddings. The exploitation of continuous word representations is motivated by the fact that ASR error detection consists on locating the possible linguistic or acoustic incongruities in automatic transcriptions. The aim is therefore to find the appropriate word representation which makes it possible to capture pertinent information in order to be able to detect these anomalies. Our contribution in this thesis concerns several initiatives. First, we start with a preliminary study in which we propose a neural architecture a...
Browsing through large volumes of spoken audio is known to be a challenging task for end users. One ...
ASR Error Detection (AED) models aim to post-process the output of Automatic Speech Recognition (ASR...
International audienceLarge vocabulary automatic speech recognition (ASR) technologies perform well ...
Les méthodes de compréhension de la parole visent à extraire des éléments de sens pertinents du sign...
International audienceThis paper addresses the problem of automatic speech recognition (ASR) error d...
This thesis is a part of the emergence of deep learning and focuses on spoken language understanding...
Over the last years, many advances have been made in the field of Automatic Speech Recognition (ASR)...
This thesis is a part of the emergence of deep learning and focuses on spoken language understanding...
This paper addresses errors in continuous Automatic Speech Recognition (ASR) in two stages: error de...
Over the last years, many advances have been made in the field of Automatic Speech Recognition (ASR)...
International audienceEvaluating transcriptions from automatic speech recognition (ASR) systems is a...
Speech based human-machine interaction and natural language understanding applications have seen a r...
An End-Of-Turn Detection Module (EOTD-M) is an essential component of au- tomatic Spoken Dialogue Sy...
International audienceEvaluating transcriptions from automatic speech recognition (ASR) systems is a...
Thesis (Ph.D.)--University of Washington, 2015Automatic speech recognition (ASR), the transcription ...
Browsing through large volumes of spoken audio is known to be a challenging task for end users. One ...
ASR Error Detection (AED) models aim to post-process the output of Automatic Speech Recognition (ASR...
International audienceLarge vocabulary automatic speech recognition (ASR) technologies perform well ...
Les méthodes de compréhension de la parole visent à extraire des éléments de sens pertinents du sign...
International audienceThis paper addresses the problem of automatic speech recognition (ASR) error d...
This thesis is a part of the emergence of deep learning and focuses on spoken language understanding...
Over the last years, many advances have been made in the field of Automatic Speech Recognition (ASR)...
This thesis is a part of the emergence of deep learning and focuses on spoken language understanding...
This paper addresses errors in continuous Automatic Speech Recognition (ASR) in two stages: error de...
Over the last years, many advances have been made in the field of Automatic Speech Recognition (ASR)...
International audienceEvaluating transcriptions from automatic speech recognition (ASR) systems is a...
Speech based human-machine interaction and natural language understanding applications have seen a r...
An End-Of-Turn Detection Module (EOTD-M) is an essential component of au- tomatic Spoken Dialogue Sy...
International audienceEvaluating transcriptions from automatic speech recognition (ASR) systems is a...
Thesis (Ph.D.)--University of Washington, 2015Automatic speech recognition (ASR), the transcription ...
Browsing through large volumes of spoken audio is known to be a challenging task for end users. One ...
ASR Error Detection (AED) models aim to post-process the output of Automatic Speech Recognition (ASR...
International audienceLarge vocabulary automatic speech recognition (ASR) technologies perform well ...