Towards Hierarchical Spoken Language Dysfluency Modeling
This addresses the bottleneck in speech therapy and language learning by providing an AI solution for disfluency modeling, though it appears incremental as an extension of an existing method.
The paper tackles the problem of speech disfluency modeling for speech therapy and language learning by introducing a hierarchical approach that addresses transcription and detection, eliminating the need for extensive manual annotation, with experimental findings showing effectiveness and reliability.
Speech disfluency modeling is the bottleneck for both speech therapy and language learning. However, there is no effective AI solution to systematically tackle this problem. We solidify the concept of disfluent speech and disfluent speech modeling. We then present Hierarchical Unconstrained Disfluency Modeling (H-UDM) approach, the hierarchical extension of UDM that addresses both disfluency transcription and detection to eliminate the need for extensive manual annotation. Our experimental findings serve as clear evidence of the effectiveness and reliability of the methods we have introduced, encompassing both transcription and detection tasks.