# STSM-FiLM: A FiLM-Conditioned Neural Architecture for Time-Scale Modification of Speech

arXiv: https://arxiv.org/abs/2510.02672 · HTML: https://mlsanity.com/paper/2510.02672/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Oct 2025.

## Built on by (most cited first, 1 of 1)

- [Predicting Postprandial Glycemic Response from Meal Images, Clinical Variables, and Gut Microbiome Information](https://mlsanity.com/paper/2609.24453/) (2026)

## Abstract (arXiv)

Time-Scale Modification (TSM) of speech aims to alter the playback rate of audio without changing its pitch. While classical methods like Waveform Similarity-based Overlap-Add (WSOLA) provide strong baselines, they often introduce artifacts under non-stationary or extreme stretching conditions. We propose STSM-FILM - a fully neural architecture that incorporates Feature-Wise Linear Modulation (FiLM) to condition the model on a continuous speed factor. By supervising the network using WSOLA-generated outputs, STSM-FILM learns to mimic alignment and synthesis behaviors while benefiting from representations learned through deep learning. We explore four encoder-decoder variants: STFT-HiFiGAN, WavLM-HiFiGAN, Whisper-HiFiGAN, and EnCodec, and demonstrate that STSM-FILM is capable of producing perceptually consistent outputs across a wide range of time-scaling factors. Overall, our results demonstrate the potential of FiLM-based conditioning to improve the generalization and flexibility of neural TSM models.