Transcription free filler word detection with Neural semi-CRFs
This addresses the problem of filler word detection for speech processing applications where ASR systems are inaccessible due to budget, language, or computational constraints, representing an incremental advance.
The paper tackled filler word detection without relying on ASR transcriptions, achieving an absolute F1 improvement of 6.4% (segment level) and 3.1% (event level) on the PodcastFillers dataset using S4 and neural semi-CRFs.
Non-linguistic filler words, such as "uh" or "um", are prevalent in spontaneous speech and serve as indicators for expressing hesitation or uncertainty. Previous works for detecting certain non-linguistic filler words are highly dependent on transcriptions from a well-established commercial automatic speech recognition (ASR) system. However, certain ASR systems are not universally accessible from many aspects, e.g., budget, target languages, and computational power. In this work, we investigate filler word detection system that does not depend on ASR systems. We show that, by using the structured state space sequence model (S4) and neural semi-Markov conditional random fields (semi-CRFs), we achieve an absolute F1 improvement of 6.4% (segment level) and 3.1% (event level) on the PodcastFillers dataset. We also conduct a qualitative analysis on the detected results to analyze the limitations of our proposed system.