Morse Code-Enabled Speech Recognition for Individuals with Visual and Hearing Impairments
Ritabrata Roy Choudhury
TL;DR
This work introduces a two-layer pipeline that first performs speech-to-text using a Google-based ASR system and then converts the resulting text into Morse code via a dedicated dictionary, outputting signals suitable for tactile interpretation. The main novelty is the integration of a Morse-code output layer with standard ASR to serve individuals with hearing, speech, or cognitive impairments. Empirical results on recorded audio show a $WER$ of $10.18\%$ and an accuracy of $89.82\%$, with a 600-sentence benchmark yielding $81\%$ correct sentences, surpassing the Bing Speech API and IBM Watson STT in that setting. The work highlights the potential of Morse-code-based interfaces to expand accessibility, including tactile feedback on the arm, and discusses future directions such as Braille or broader militaristic applications of Morse signaling.
Abstract
The proposed model aims to develop a speech recognition technology for hearing, speech, or cognitively disabled people. All the available technology in the field of speech recognition doesn't come with an interface for communication for people with hearing, speech, or cognitive disabilities. The proposed model proposes the speech from the user, is transmitted to the speech recognition layer where it is converted into text and then that text is then transmitted to the morse code conversion layer where the morse code of the corresponding speech is given as the output. The accuracy of the model is completely dependent on speech recognition, as the morse code conversion is a process. The model is tested with recorded audio files with different parameters. The proposed model's WER and accuracy are both determined to be 10.18% and 89.82%, respectively.