# Transcription free filler word detection with Neural semi-CRFs

arXiv: https://arxiv.org/abs/2303.06475 · HTML: https://mlsanity.com/paper/2303.06475/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 30 references that are in the map.
- First posted on arXiv 11 Mar 2023.

## Builds on (most cited first, 10 of 10)

- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [On Layer Normalization in the Transformer Architecture](https://mlsanity.com/paper/2002.04745/) (2020)
- [Simplified State Space Layers for Sequence Modeling](https://mlsanity.com/paper/2208.04933/) (2022)
- [Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers](https://mlsanity.com/paper/2110.13985/) (2021)
- [It's Raw! Audio Generation with State-Space Models](https://mlsanity.com/paper/2202.09729/) (2022)
- [Multi-Task Self-Supervised Learning for Disfluency Detection](https://mlsanity.com/paper/1908.05378/) (2019)
- [Disfluency Detection with Unlabeled Data and Small BERT Models](https://mlsanity.com/paper/2104.10769/) (2021)
- [Disfluency Detection using Auto-Correlational Neural Networks](https://mlsanity.com/paper/1808.09092/) (2018)
- [Segmental Recurrent Neural Networks for End-to-end Speech Recognition](https://mlsanity.com/paper/1603.00223/) (2016)
- [Filler Word Detection and Classification: A Dataset and Benchmark](https://mlsanity.com/paper/2203.15135/) (2022)

## Built on by (most cited first, 2 of 2)

- [Audio Mamba: Bidirectional State Space Model for Audio Representation Learning](https://mlsanity.com/paper/2406.03344/) (2024)
- [LearnerVoice: A Dataset of Non-Native English Learners' Spontaneous Speech](https://mlsanity.com/paper/2407.04280/) (2024)

## Abstract (arXiv)

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.