# FiLM-Based Speaker Conditioning of a SpeechLLM for Pathological Speech Recognition

arXiv: https://arxiv.org/abs/2606.06211 · HTML: https://mlsanity.com/paper/2606.06211/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 19 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 14 of 14)

- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [Kimi-Audio Technical Report](https://mlsanity.com/paper/2504.18425/) (2025)
- [Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models](https://mlsanity.com/paper/2507.08128/) (2025)
- [Qwen3-ASR Technical Report](https://mlsanity.com/paper/2601.21337/) (2026)
- [Ministral 3](https://mlsanity.com/paper/2601.08584/) (2026)
- [Voxtral](https://mlsanity.com/paper/2507.13264/) (2025)
- [VoxBlink2: A 100K+ Speaker Recognition Corpus and the Open-Set Speaker-Identification Benchmark](https://mlsanity.com/paper/2407.11510/) (2024)
- [Speaker adaptation for Wav2vec2 based dysarthric ASR](https://mlsanity.com/paper/2204.00770/) (2022)
- [NeuroVoz: a Castillian Spanish corpus of parkinsonian speech](https://mlsanity.com/paper/2403.02371/) (2024)
- [The Interspeech 2025 Speech Accessibility Project Challenge](https://mlsanity.com/paper/2507.22047/) (2025)
- [Use of Speech Impairment Severity for Dysarthric Speech Recognition](https://mlsanity.com/paper/2305.10659/) (2023)
- [Personalized Fine-Tuning with Controllable Synthetic Speech from LLM-Generated Transcripts for Dysarthric Speech Recognition](https://mlsanity.com/paper/2505.12991/) (2025)

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

- [Choosing a PEFT Variant for Per-Patient Dysarthric ASR: A Single-Speaker Case Study on Two ASR Bases](https://mlsanity.com/paper/2609.02735/) (2026)

## Abstract (arXiv)

Automatic speech recognition (ASR) has advanced remarkably for standard speech; however, pathological speech from neurological conditions remains a significant challenge. We investigate speaker conditioning via Feature-wise Linear Modulation (FiLM), injecting x-vector-derived information into each transformer layer of a frozen ASR encoder to adapt internal representations to individual pathological speakers without modifying base model weights. We benchmark this for the ASR task against standard and parameter-efficient fine-tuning baselines, complemented by post-processing, on Spanish and English pathological speech. Additionally, we evaluate if the adapted model preserves the ability to answer speech-related questions. Results show that speaker-conditioned ASR is competitive with established adaptation strategies while retaining performance on non-conditioned speech.