Learning out-of-vocabulary words in automatic speech recognition
L Qin - 2013 - search.proquest.com
Abstract Out-of-vocabulary (OOV) words are unknown words that appear in the testing
speech but not in the recognition vocabulary. They are usually important content words such …
speech but not in the recognition vocabulary. They are usually important content words such …
[PDF][PDF] CRF-based combination of contextual features to improve a posteriori word-level confidence measures
J Fayolle, F Moreau, C Raymond… - … Annual Conference of …, 2010 - academia.edu
The paper addresses the issue of confidence measure reliability provided by automatic
speech recognition systems for use in various spoken language processing applications. In …
speech recognition systems for use in various spoken language processing applications. In …
Asr performance prediction on unseen broadcast programs using convolutional neural networks
Z Elloumi, L Besacier, O Galibert… - … , Speech and Signal …, 2018 - ieeexplore.ieee.org
In this paper, we address a relatively new task: prediction of ASR performance on unseen
broadcast programs. We first propose an heterogenous French corpus dedicated to this task …
broadcast programs. We first propose an heterogenous French corpus dedicated to this task …
“Can you give me another word for hyperbaric?”: Improving speech translation using targeted clarification questions
We present a novel approach for improving communication success between users of
speech-to-speech translation systems by automatically detecting errors in the output of …
speech-to-speech translation systems by automatically detecting errors in the output of …
[PDF][PDF] Learning OOV through semantic relatedness in spoken dialog systems.
Ensuring language coverage in dialog systems can be a challenge, since the language in a
domain may drift over time, creating a mismatch between the original training data and …
domain may drift over time, creating a mismatch between the original training data and …
Document level semantic context for retrieving OOV proper names
I Sheikh, I Ulina, D Fohr… - 2016 IEEE International …, 2016 - ieeexplore.ieee.org
Recognition of Proper Names (PNs) in speech is important for content based indexing and
browsing of audio-video data. However, many PNs are Out-Of-Vocabulary (OOV) words for …
browsing of audio-video data. However, many PNs are Out-Of-Vocabulary (OOV) words for …
Using syntactic and confusion network structure for out-of-vocabulary word detection
This paper addresses the problem of detecting words that are out-of-vocabulary (OOV) for a
speech recognition system to improve automatic speech translation. The detection system …
speech recognition system to improve automatic speech translation. The detection system …
Étude sur les représentations continues de mots appliquées à la détection automatique des erreurs de reconnaissance de la parole
S Ghannay - 2017 - theses.hal.science
Nous abordons, dans cette thèse, une étude sur les représentations continues de mots (en
anglais word embeddings) appliquées à la détection automatique des erreurs dans les …
anglais word embeddings) appliquées à la détection automatique des erreurs dans les …
Error type classification and word accuracy estimation using alignment features from word confusion network
This paper addresses error type classification in continuous speech recognition (CSR). In
CSR, errors are classified into three types, namely, the substitution, insertion and deletion …
CSR, errors are classified into three types, namely, the substitution, insertion and deletion …
Word confidence estimation for speech translation
Word Confidence Estimation (WCE) for machine transla-tion (MT) or automatic speech
recognition (ASR) consists in judging each word in the (MT or ASR) hypothesis as correct or …
recognition (ASR) consists in judging each word in the (MT or ASR) hypothesis as correct or …