Automatic Speech Recognition Services

Glasser, Abraham

doi:10.1145/3290607.3308461

Cited by 15 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If these AI-based tools are deployed in critical or popular applications, some groups of people will be disadvantaged, including people with disabilities: For instance, in our own work, we have found that ASR systems, which are increasingly used for interaction with mobile devices or personal assistants (e.g. Siri or Alexa), do not work well for speech from DHH users [9]. The poor performance on these voices is likely due to a lack of inclusion of speech from people who are DHH in the training data sets used to build modern ASR systems.…”

Section: Need For Inclusion In Training Datamentioning

confidence: 94%

Artificial intelligence fairness in the context of accessibility research on intelligent systems for people who are deaf or hard of hearing

Kafle

Glasser

Al-khazraji

et al. 2020

SIGACCESS Access. Comput.

Self Cite

View full text Add to dashboard Cite

We discuss issues of Artificial Intelligence (AI) fairness for people with disabilities, with examples drawn from our research on HCI for AI-based systems for people who are Deaf or Hard of Hearing (DHH). In particular, we discuss the need for inclusion of data from people with disabilities in training sets, the lack of interpretability of AI systems, ethical responsibilities of access technology researchers and companies, the need for appropriate evaluation metrics for AI-based access technologies (to determine if they are ready to be deployed and if they can be trusted by users), and the ways in which AI systems influence human behavior and influence the set of abilities needed by users to successfully interact with computing systems.

show abstract

Section: Need For Inclusion In Training Datamentioning

confidence: 94%

Artificial intelligence fairness in the context of accessibility research on intelligent systems for people who are deaf or hard of hearing

Kafle

Glasser

Al-khazraji

et al. 2020

SIGACCESS Access. Comput.

Self Cite

View full text Add to dashboard Cite

show abstract

Quantification of Automatic Speech Recognition System Performance on d/Deaf and Hard of Hearing Speech

Zhao,

Choi,

Koenecke

et al. 2024

The Laryngoscope

View full text Add to dashboard Cite

ObjectiveTo evaluate the performance of commercial automatic speech recognition (ASR) systems on d/Deaf and hard‐of‐hearing (d/Dhh) speech.MethodsA corpus containing 850 audio files of d/Dhh and normal hearing (NH) speech from the University of Memphis Speech Perception Assessment Laboratory was tested on four speech‐to‐text application program interfaces (APIs): Amazon Web Services, Microsoft Azure, Google Chirp, and OpenAI Whisper. We quantified the Word Error Rate (WER) of API transcriptions for 24 d/Dhh and nine NH participants and performed subgroup analysis by speech intelligibility classification (SIC), hearing loss (HL) onset, and primary communication mode.ResultsMean WER averaged across APIs was 10 times higher for the d/Dhh group (52.6%) than the NH group (5.0%). APIs performed significantly worse for “low” and “medium” SIC (85.9% and 46.6% WER, respectively) as compared to “high” SIC group (9.5% WER, comparable to NH group). APIs performed significantly worse for speakers with prelingual HL relative to postlingual HL (80.5% and 37.1% WER, respectively). APIs performed significantly worse for speakers primarily communicating with sign language (70.2% WER) relative to speakers with both oral and sign language communication (51.5%) or oral communication only (19.7%).ConclusionCommercial ASR systems underperform for d/Dhh individuals, especially those with “low” and “medium” SIC, prelingual onset of HL, and sign language as primary communication mode. This contrasts with Big Tech companies' promises of accessibility, indicating the need for ASR systems ethically trained on heterogeneous d/Dhh speech data.Level of Evidence3 Laryngoscope, 2024

show abstract

Conversational Agents to Promote Children’s Verbal Communication Skills

Catania

Spitale

Cosentino

et al. 2021

Chatbot Research and Design

View full text Add to dashboard Cite

The fundamentals of verbal communication skills are developed during childhood, and existing studies pinpoint the benefits of stimulating language and expression skills from an early age. Our research is a preliminary evaluation of conversational technology to support this process. In this paper, we describe the design process of a speech-based conversational agent for children, which involved a Wizard-of-Oz empirical study with 20 primary school children aged 9-10 y.o. in order to identify the design guidelines for the automated version of the system. Our agent is called ISI, is integrated into a web application and exploits oral and visual interaction modes. ISI enables children to practice verbal skills related to the description of a person's physical characteristics. It provides opportunities for them to learn and use words and linguistic constructs. Also, ISI permits to develop their body awareness and selfexpression (when describing their self) or the attention to "the other" (when describing someone else). ISI engages users in a speech-based conversational flow composed of two main repeated steps. It talks to the children and stimulates them with questions about a specific part of their body (e.g., "What color is your hair?"). When the users describe the required feature adequately, ISI provides a cheerful real-time visual representation of the answer; otherwise, it provides hints.

show abstract

Automatic Speech Recognition Services

Cited by 15 publications

References 4 publications

Artificial intelligence fairness in the context of accessibility research on intelligent systems for people who are deaf or hard of hearing

Artificial intelligence fairness in the context of accessibility research on intelligent systems for people who are deaf or hard of hearing

Quantification of Automatic Speech Recognition System Performance on d/Deaf and Hard of Hearing Speech

Conversational Agents to Promote Children’s Verbal Communication Skills

Contact Info

Product

Resources

About