DisfluencyFixer: A tool to enhance Language Learning through Speech To Speech Disfluency Correction
This addresses the need for language learners to improve speech fluency, but it is incremental as it combines existing ASR, DC, and TTS models into a pipeline.
The paper tackles the problem of disfluent speech in language learning by developing DisfluencyFixer, a tool that corrects disfluencies in English and Hindi speech, achieving subjective scores of 4.26, 4.29, and 4.42 out of 5 for ASR, DC, and ease-of-use.
Conversational speech often consists of deviations from the speech plan, producing disfluent utterances that affect downstream NLP tasks. Removing these disfluencies is necessary to create fluent and coherent speech. This paper presents DisfluencyFixer, a tool that performs speech-to-speech disfluency correction in English and Hindi using a pipeline of Automatic Speech Recognition (ASR), Disfluency Correction (DC) and Text-To-Speech (TTS) models. Our proposed system removes disfluencies from input speech and returns fluent speech as output along with its transcript, disfluency type and total disfluency count in source utterance, providing a one-stop destination for language learners to improve the fluency of their speech. We evaluate the performance of our tool subjectively and receive scores of 4.26, 4.29 and 4.42 out of 5 in ASR performance, DC performance and ease-of-use of the system. Our tool can be accessed openly at the following link.