SearcharxivSearch

arXiv · 2110.04385

Individualized Hear-through For Acoustic Transparency Using PCA-Based Sound Pressure Estimation At The Eardrum

Abstract

The hear-through functionality on hearing devices, which allows hearing equivalent to the open-ear while providing the possibility to modify the sound pressure at the eardrum in a desired manner, has drawn great attention from researchers in recent years. To this end, the output of the device is processed by means of an equalization filter, such that the transfer function between external sound sources and the eardrum is equivalent for the open-ear and the aided condition with the device in the ear. To achieve an ideal performance, the equalization filter design assumes the exact knowledge of all the relevant acoustic transfer functions. A particular challenge is the transfer function between the hearing device receiver and the eardrum, which is difficult to obtain in practice as it requires additional probe-tube measurements. In this work, we address this issue by proposing an individualized hear-through equalization filter design that leverages the measurement of the so-called secondary path to predict the sound pressure at the eardrum. Experimental results using real-ear measured transfer functions confirm that the proposed method achieves a good sound quality compared to the open-ear while outperforming filter designs that do not leverage the proposed estimator.

Explore related subjects

Keep this discovery

BibTeXRIS

Wenyu Jin, Tim Schoof, Henning Schepker. 2021-10-08. Individualized Hear-through For Acoustic Transparency Using PCA-Based Sound Pressure Estimation At The Eardrum. https://arxiv.org/abs/2110.04385

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

Diarization Error Decomposition Under Pause Annotation Ambiguity

Speaker diarization evaluation is sensitive to ambiguity in pause annotation, which can inflate diarization error rate (DER) or obscure genuine model errors. We show that morphological closing, which has been used for pause-tolerant diarization evaluation, discards segment-level distinctions. Instead, we propose an exact, overlap-aware decomposition of standard DER into a pause-attributable component, consisting of errors compatible with pause filling, and a residual core component that can serve as a proxy for intrinsic diarization errors. The decomposition leaves DER unchanged, while the pause-attributable and core components vary monotonically with the pause threshold and eventually saturate. Experiments spanning synthetic transformations, annotation mismatch, cross-domain evaluation, and tight-boundary diarization show that the decomposition reveals error sources not apparent from standard DER.

eess.AS

Less can be More: What Aspects of Speech Drive End-of-Turn Detection

In conversational AI, detecting when a speaker has finished talking is crucial for natural turn taking. While recent work incorporates semantics, the relative contribution of different modalities remains unclear. We present a controlled ablation of acoustic, prosodic, and semantic signals for streaming end of turn detection using a lightweight trimodal classifier. Under identical training conditions, the acoustic prosodic combination achieves the best balance of accuracy and latency, achieving utterance F1 of 0.93 with 7.8% false alarms at 400ms median latency. Adding text increases premature detections without improving performance. Feature space analysis confirms that prosodic features have the strongest class separability, while text representations overlap substantially. These findings suggest that turn-taking is primarily conveyed through intonation and silence patterns rather than semantic completeness, enabling faster and more reliable systems without expensive text inference.

eess.AS

Downstream-Task-Aware Unified Source Separation

Task-aware unified source separation (TUSS) enables a single model to handle diverse separation tasks by conditioning on input prompts. However, conventional TUSS does not account for downstream task requirements, such as whether the enhanced speech will be used for human listening or automatic speech recognition (ASR). In this paper, we propose a prompt extension framework for TUSS that incorporates downstream task information into the input prompts and switches the loss function according to the given prompt during training, enabling outputs with different signal characteristics at inference time. Specifically, we introduce an ASR-dedicated prompt paired with a regularized loss function that reduces speech artifacts to improve ASR robustness, while the standard prompt is paired with the conventional SNR loss function. Experiments on the LibriSpeech and JNAS corpora demonstrate that the proposed joint-training scheme enables a single model to improve ASR performance over noisy input across a wide range of SNR conditions by selecting the ASR-dedicated prompt, while maintaining general speech enhancement quality when the standard prompt is used.

eess.AS