Deaf and hard of hearing individuals regularly rely on captioning while watching live TV. Live TV captioning is evaluated by regulatory agencies using various caption evaluation metrics. However, caption evaluation metrics are often not informed by preferences of DHH users or how meaningful the captions are. There is a need to construct caption evaluation metrics that take the relative importance of words in transcript into account. We conducted correlation analysis between two types of word embeddings and human-annotated labelled word-importance scores in existing corpus. We found that normalized contextualized word embeddings generated using BERT correlated better with manually annotated importance scores than word2vec-based word embeddings. We make available a pairing of word embeddings and their human-annotated importance scores. We also provide proof-of-concept utility by training word importance models, achieving an F1-score of 0.57 in the 6-class word importance classification task.

Research has explored the use of automatic text simplification (ATS), which consists of techniques to make text simpler to read, to provide reading assistance to Deaf and Hard-of-hearing (DHH) adults with various literacy levels. Prior work in this area has identified interest in and benefits from ATS-based reading assistance tools. However, no prior work on ATS has gathered judgements from DHH adults as to what constitutes complex text. Thus, following approaches in prior NLP work, this paper contributes new word-complexity judgements from 11 DHH adults on a dataset of 15,000 English words that had been previously annotated by L2 speakers, which we also augmented to include automatic annotations of linguistic characteristics of the words. Additionally, we conduct a supplementary analysis of the interaction effect between the linguistic characteristics of the words and the groups of annotators. This analysis highlights the importance of collecting judgements from DHH adults for training ATS systems, as it revealed statistically significant interaction effects for nearly all of the linguistic characteristics of the words.

We are releasing a dataset containing videos of both fluent and non-fluent signers using American Sign Language (ASL), which were collected using a Kinect v2 sensor. This dataset was collected as a part of a project to develop and evaluate computer vision algorithms to support new technologies for automatic detection of ASL fluency attributes. A total of 45 fluent and non-fluent participants were asked to perform signing homework assignments that are similar to the assignments used in introductory or intermediate level ASL courses. The data is annotated to identify several aspects of signing including grammatical features and non-manual markers. Sign language recognition is currently very data-driven and this dataset can support the design of recognition technologies, especially technologies that can benefit ASL learners. This dataset might also be interesting to ASL education researchers who want to contrast fluent and non-fluent signing.

Deaf signers who wish to communicate in their native language frequently share videos on the Web. However, videos cannot preserve privacy—as is often desirable for discussion of sensitive topics—since both hands and face convey critical linguistic information and therefore cannot be obscured without degrading communication. Deaf signers have expressed interest in video anonymization that would preserve linguistic content. However, attempts to develop such technology have thus far shown limited success. We are developing a new method for such anonymization, with input from ASL signers. We modify a motion-based image animation model to generate high-resolution videos with the signer identity changed, but with the preservation of linguistically significant motions and facial expressions. An asymmetric encoder-decoder structured image generator is used to generate the high-resolution target frame from the low-resolution source frame based on the optical flow and confidence map. We explicitly guide the model to attain a clear generation of hands and faces by using bounding boxes to improve the loss computation. FID and KID scores are used for the evaluation of the realism of the generated frames. This technology shows great potential for practical applications to benefit deaf signers.

Much of the world’s population experiences some form of disability during their lifetime. Caution must be exercised while designing natural language processing (NLP) systems to prevent systems from inadvertently perpetuating ableist bias against people with disabilities, i.e., prejudice that favors those with typical abilities. We report on various analyses based on word predictions of a large-scale BERT language model. Statistically significant results demonstrate that people with disabilities can be disadvantaged. Findings also explore overlapping forms of discrimination related to interconnected gender and race identities.

We have collected a new dataset consisting of color and depth videos of fluent American Sign Language (ASL) signers performing sequences of 100 ASL signs from a Kinect v2 sensor. This directed dataset had originally been collected as part of an ongoing collaborative project, to aid in the development of a sign-recognition system for identifying occurrences of these 100 signs in video. The set of words consist of vocabulary items that would commonly be learned in a first-year ASL course offered at a university, although the specific set of signs selected for inclusion in the dataset had been motivated by project-related factors. Given increasing interest among sign-recognition and other computer-vision researchers in red-green-blue-depth (RBGD) video, we release this dataset for use by the research community. In addition to the RGB video files, we share depth and HD face data as well as additional features of face, hands, and body produced through post-processing of this data.

Prosodic cues in conversational speech aid listeners in discerning a message. We investigate whether acoustic cues in spoken dialogue can be used to identify the importance of individual words to the meaning of a conversation turn. Individuals who are Deaf and Hard of Hearing often rely on real-time captions in live meetings. Word error rate, a traditional metric for evaluating automatic speech recognition (ASR), fails to capture that some words are more important for a system to transcribe correctly than others. We present and evaluate neural architectures that use acoustic features for 3-class word importance prediction. Our model performs competitively against state-of-the-art text-based word-importance prediction models, and it demonstrates particular benefits when operating on imperfect ASR output.