End-to-end speech recognition modeling from de-identified data

Martin Flechl; Shou-Chun Yin; Junho Park; Peter Skala

Home/Archive/arXiv

arXiv · 2207.05469

End-to-end speech recognition modeling from de-identified data

Martin Flechl·Shou-Chun Yin·Junho Park·Peter Skala

View original source ↗Read source document ↗Export metadata ↓

Abstract

De-identification of data used for automatic speech recognition modeling is a critical component in protecting privacy, especially in the medical domain. However, simply removing all personally identifiable information (PII) from end-to-end model training data leads to a significant performance degradation in particular for the recognition of names, dates, locations, and words from similar categories. We propose and evaluate a two-step method for partially recovering this loss. First, PII is identified, and each occurrence is replaced with a random word sequence of the same category. Then, corresponding audio is produced via text-to-speech or by splicing together matching audio fragments extracted from the corpus. These artificial audio/label pairs, together with speaker turns from the original data without PII, are used to train models. We evaluate the performance of this method on in-house data of medical conversations and observe a recovery of almost the entire performance degradation in the general word error rate while still maintaining a strong diarization performance. Our main focus is the improvement of recall and precision in the recognition of PII-related words. Depending on the PII category, between $50\% - 90\%$ of the performance degradation can be recovered using our proposed method.

Explore related subjects

eess.AS cs.CR cs.LG cs.SD

Keep this discovery

BibTeX RIS

Martin Flechl, Shou-Chun Yin, Junho Park, Peter Skala. 2022-07-12. End-to-end speech recognition modeling from de-identified data. https://arxiv.org/abs/2207.05469

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

KEEP EXPLORING

Related papers

arXiv2026

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↗

arXiv2026

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↗

arXiv2026

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↗