Advances in Speech Enhancement using Audio Signal Processing Techniques

12.5K
views
11
authors
4
articles
Editors
3
Impact
Loading...
2,632 views
9 citations
Original Research
11 March 2022
Dual-Microphone Speech Reinforcement System With Howling-Control for In-Car Speech Communication
Yehav Alkaher
 and 
Israel Cohen 

In this paper, we address the problem of dual-microphone speech reinforcement for improving in-car speech communication via howling control. A speech reinforcement system acquires speech from a speaker’s microphone and delivers it to the other listeners in the car cabin through loudspeakers. A car cabin’s small space makes it vulnerable to acoustic feedback, resulting in the appearance of howling noises. The proposed system aims to maintain a desired high amplification gain over time while not compromising the output speech quality. The dual-microphone system consists of a microphone for speech acquisition and another microphone that monitors the environment for howling detection, where its location depends on its howling detection sensitivity. The proposed algorithm contains a gain-control segment based on the magnitude-slope-deviation measure, which reduces the amplification-gain in the case of howling detection. To find the optimal locations of the howling-detection microphone in the cabin, for a devised set of scenarios, a Pareto optimization method is applied. The Pareto optimization considers the bi-objective nature of the problem, i.e., minimizing both the relative gain-reduction and the overall speech distortion. It is shown that the proposed dual-microphone system outperforms a single-microphone-based system. The performance improvement is demonstrated by showing the higher howling detection sensitivity of the dual-microphone system. Additionally, a microphone constellation design process, for optimal howling detection, is provided through the utilization of the Pareto fronts and anti-fronts approach.

2,863 views
5 citations
Original Research
07 March 2022

In this paper we present Active Inference-Based Design Agent (AIDA), which is an active inference-based agent that iteratively designs a personalized audio processing algorithm through situated interactions with a human client. The target application of AIDA is to propose on-the-spot the most interesting alternative values for the tuning parameters of a hearing aid (HA) algorithm, whenever a HA client is not satisfied with their HA performance. AIDA interprets searching for the “most interesting alternative” as an issue of optimal (acoustic) context-aware Bayesian trial design. In computational terms, AIDA is realized as an active inference-based agent with an Expected Free Energy criterion for trial design. This type of architecture is inspired by neuro-economic models on efficient (Bayesian) trial design in brains and implies that AIDA comprises generative probabilistic models for acoustic signals and user responses. We propose a novel generative model for acoustic signals as a sum of time-varying auto-regressive filters and a user response model based on a Gaussian Process Classifier. The full AIDA agent has been implemented in a factor graph for the generative model and all tasks (parameter learning, acoustic context classification, trial design, etc.) are realized by variational message passing on the factor graph. All verification and validation experiments and demonstrations are freely accessible at our GitHub repository.

3,290 views
7 citations
Recommended Research Topics
Frontiers Logo

Frontiers in Signal Processing

Recent Advances in Audio Source Separation
Edited by Nikolaos Mitianoudis, Wenwu Wang, Nobutaka Ito, Sebastian Ewert
26.5K
views
16
authors
3
articles