Identifying Disfluencies in Natural Speech

Posted by Dan Walker and Dan Liebling, Software Engineers, Google Research

People don’t write in the same way that they speak. Written language is controlled and deliberate, whereas transcripts of spontaneous speech (like interviews) are hard to read because speech is disorganized and less fluent. One aspect that makes speech transcripts particularly difficult to read is disfluency, which includes self-corrections, repetitions, and filled pauses (e.g., words like “umm”, and “you know”). Following is an example …

automatic speech recognition naacl natural semi-supervised learning speech