Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2501.13642

Learning-based A Posteriori Speech Presence Probability Estimation and Applications

Shuai Tao·Jesper Rindom Jensen·Yang Xiang·Himavanth Reddy·Qingzheng Zhang·Mads Græsbøll Christensen
View original source ↗Read source document ↗Export metadata ↓

Abstract

The a posteriori speech presence probability (SPP) is the fundamental component of noise power spectral density (PSD) estimation, which can contribute to speech enhancement and speech recognition systems. Most existing SPP estimators can estimate SPP accurately from the background noise. Nevertheless, numerous challenges persist, including the difficulty of accurately estimating SPP from non-stationary noise with statistics-based methods and the high latency associated with deep learning-based approaches. This paper presents an improved SPP estimation approach based on deep learning to achieve higher SPP estimation accuracy, especially in non-stationary noise conditions. To promote the information extraction performance of the DNN, the global information of the observed signal and the local information of the decoupled frequency bins from the observed signal are connected as hybrid global-local information. The global information is extracted by one encoder. Then, one decoder and two fully connected layers are used to estimate SPP from the information of residual connection. To evaluate the performance of our proposed SPP estimator, the noise PSD estimation and speech enhancement tasks are performed. In contrast to existing minimum mean-square error (MMSE)-based noise PSD estimation approaches, the noise PSD is estimated by the sub-optimal MMSE based on the current frame SPP estimate without smoothing. Directed by the noise PSD estimate, a standard speech enhancement framework, the log spectral amplitude estimator, is employed to extract clean speech from the observed signal. From the experimental results, we can confirm that our proposed SPP estimator can achieve high noise PSD estimation accuracy and speech enhancement performance while requiring low model complexity.

Explore related subjects

eess.AS

Keep this discovery

BibTeXRIS

Shuai Tao, Jesper Rindom Jensen, Yang Xiang, Himavanth Reddy, Qingzheng Zhang, Mads Græsbøll Christensen. 2025-01-23. Learning-based A Posteriori Speech Presence Probability Estimation and Applications. https://arxiv.org/abs/2501.13642

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↗