# Language Modelling for Sound Event Detection with Teacher Forcing and Scheduled Sampling

arXiv: https://arxiv.org/abs/1907.08506 · HTML: https://mlsanity.com/paper/1907.08506/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2019.

## Built on by (most cited first, 5 of 5)

- [Flipped Classroom: Effective Teaching for Time Series Forecasting](https://mlsanity.com/paper/2210.08959/) (2022)
- [Recurrent Brain Graph Mapper for Predicting Time-Dependent Brain Graph Evaluation Trajectory](https://mlsanity.com/paper/2110.11237/) (2021)
- [Language-based Audio Moment Retrieval](https://mlsanity.com/paper/2409.15672/) (2024)
- [tinyCLAP: Distilling Constrastive Language-Audio Pretrained Models](https://mlsanity.com/paper/2311.14517/) (2023)
- [Micro-level Reserving for General Insurance Claims using a Long Short-Term Memory Network](https://mlsanity.com/paper/2201.13267/) (2022)

## Abstract (arXiv)

A sound event detection (SED) method typically takes as an input a sequence of audio frames and predicts the activities of sound events in each frame. In real-life recordings, the sound events exhibit some temporal structure: for instance, a "car horn" will likely be followed by a "car passing by". While this temporal structure is widely exploited in sequence prediction tasks (e.g., in machine translation), where language models (LM) are exploited, it is not satisfactorily modeled in SED. In this work we propose a method which allows a recurrent neural network (RNN) to learn an LM for the SED task. The method conditions the input of the RNN with the activities of classes at the previous time step. We evaluate our method using F1 score and error rate (ER) over three different and publicly available datasets; the TUT-SED Synthetic 2016 and the TUT Sound Events 2016 and 2017 datasets. The obtained results show an increase of 9% and 2% at the F1 (higher is better) and a decrease of 7% and 2% at ER (lower is better) for the TUT Sound Events 2016 and 2017 datasets, respectively, when using our method. On the contrary, with our method there is a decrease of 4% at F1 score and an increase of 7% at ER for the TUT-SED Synthetic 2016 dataset.