Accented speech recognition: Benchmarking, pre-training, and diverse data
Building inclusive speech recognition systems is a crucial step towards developing
technologies that speakers of all language varieties can use. Therefore, ASR systems must …
technologies that speakers of all language varieties can use. Therefore, ASR systems must …
A study of gender impact in self-supervised models for speech-to-text systems
Self-supervised models for speech processing emerged recently as popular foundation
blocks in speech processing pipelines. These models are pre-trained on unlabeled audio …
blocks in speech processing pipelines. These models are pre-trained on unlabeled audio …
Language-specific effects on automatic speech recognition errors for world Englishes
Despite recent advancements in automated speech recognition (ASR) technologies, reports
of unequal performance across speakers of different demographic groups abound. At the …
of unequal performance across speakers of different demographic groups abound. At the …
Language variation, automatic speech recognition and algorithmic bias
N Markl - 2023 - era.ed.ac.uk
In this thesis, I situate the impacts of automatic speech recognition systems in relation to
sociolinguistic theory (in particular drawing on concepts of language variation, language …
sociolinguistic theory (in particular drawing on concepts of language variation, language …
Linguistic patterns in the lexical-semantic subsystem of new public administration: typology and features
DA Okolyshev, IS Karabulatova… - Amazonia …, 2022 - amazoniainvestiga.info
The authors analyzed the confeptosphere of public administration from the position of
representation in the Rus-sian language as an area of increased interest from the controlling …
representation in the Rus-sian language as an area of increased interest from the controlling …
Improving Speech Recognition for African American English with Audio Classification
Automatic speech recognition (ASR) systems have been shown to have large quality
disparities between the language varieties they are intended or expected to recognize. One …
disparities between the language varieties they are intended or expected to recognize. One …
Multilingual TTS Accent Impressions for Accented ASR
Abstract Automatic Speech Recognition (ASR) for high-resource languages like English is
often considered a solved problem. However, most high-resource ASR systems favor …
often considered a solved problem. However, most high-resource ASR systems favor …
Goodness of Pronunciation Pipelines for OOV Problem
A Grover - arXiv preprint arXiv:2209.03787, 2022 - arxiv.org
In the following report we propose pipelines for Goodness of Pronunciation (GoP)
computation solving OOV problem at testing time using Vocab/Lexicon expansion …
computation solving OOV problem at testing time using Vocab/Lexicon expansion …
[PDF][PDF] Speech Disfluency, Repetition and Reduplication: A Survey
A Ahmad, P Bhattacharyya - cfilt.iitb.ac.in
This survey presents a comprehensive analysis of speech disfluency, repetition, and
reduplication within the context of Automatic Speech Recognition (ASR) and natural …
reduplication within the context of Automatic Speech Recognition (ASR) and natural …