# Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers

Source: [Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers](<https://www.sota2.com/research/paper/69c4bd710636e5bf4afc74d3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-18T05:00:05.624Z

Authors: Jakob Kienegger, Timo Gerkmann

Published: 2026-03-24T21:19:45.000Z

## Abstract

Deep spatially selective filters achieve high-quality enhancement with real-time capable architectures for stationary speakers of known directions. To retain this level of performance in dynamic scenarios where only the speakers' initial directions are given, accurate, yet computationally lightweight tracking algorithms become necessary. Assuming a frame-wise causal processing style, temporal feedback allows for leveraging the enhanced speech signal to improve tracking performance. In this work, we investigate strategies to incorporate the enhanced signal into lightweight tracking algorithms and autoregressively guide deep spatial filters. Our proposed Bayesian tracking algorithms are compatible with arbitrary deep spatial filters. To increase the realism of simulated trajectories during development and evaluation, we develop a synthetic data generation framework based on the social force model. Results validate that the autoregressive incorporation significantly improves the accuracy of our Bayesian trackers, resulting in superior enhancement with none or only negligibly increased computational overhead. Real-world recordings complement these findings and demonstrate the generalizability of our methods to unseen acoustic conditions.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Target Speaker Tracking on Synthetic moving-speaker dataset](<https://www.sota2.com/research/sota/target-speaker-tracking-on-synthetic-moving-speaker-dataset.md>): Target Speaker Tracking; Synthetic moving-speaker dataset; Accuracy: 87.6.

- [Target Speaker Extraction on Synthetic moving-speaker dataset](<https://www.sota2.com/research/sota/target-speaker-extraction-on-synthetic-moving-speaker-dataset.md>): Target Speaker Extraction; Synthetic moving-speaker dataset; PESQ: 2.04.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.23723>)

[PDF](<https://arxiv.org/pdf/2603.23723.pdf>)