Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 1407.3398

Speech Polarity Detection Using Hilbert Phase Information

D. Govind·Anju Susan Biju·Aguthu Smily
View original source ↗Read source document ↗Export metadata ↓

Abstract

The objective of the present work is to propose a method to automatically detect polarity of the speech signals by estimating instants of significant excitation of the vocaltract and the cosine phase of the analytic signal representation. The phase changes in the analytic signal around the Hilbert envelope (HE) peaks are found to vary according to the polarity of the given speech signal. The relevant HE peaks for the Hilbert phase analysis are selected by estimating the instants of significant excitation in speech. The speech polarity identification rate obtained for the proposed method is almost equal to the state of the art residual skewness method for speech polarity detection. The proposed method also provides the same results for the polarity detection in electro-glottogram signals. Finally, the robustness of the proposed method is confirmed from the reduced detection error rates obtained in noisy environments with various signal to noise ratios (SNRs). The MATLAB codes used for implementing the proposed method are available for download from the following link: http://nlp.amrita.edu:8080/TTS/polarityprograms.zip

Explore related subjects

cs.SD

Keep this discovery

BibTeXRIS

D. Govind, Anju Susan Biju, Aguthu Smily. 2014-07-17. Speech Polarity Detection Using Hilbert Phase Information. https://arxiv.org/abs/1407.3398

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

KEEP EXPLORING

Related papers

arXiv2026

Xiaomi-CocktailASR-1 Technical Report

Recently, large language model (LLM) based ASR models have achieved significant progress, yet they generally lack support for multi-speaker scenarios, where the cocktail party problem remains a critical bottleneck for further advancing ASR. Existing TS-ASR methods, including end-to-end architectures with speaker embeddings and latest LLM-based explorations suffer from degraded single-speaker performance and the inability to reject when the target speaker is absent. In this paper, we propose Xiaomi-CocktailASR-1, an LLM-based end-to-end TS-ASR architecture. By utilizing reference speech as voiceprint prompts, it directly transcribes the target speaker's speech without requiring speech separation. Xiaomi-CocktailASR-1 maintains competitive performance in single-speaker scenarios, comparable to mainstream ASR models. It also features a negative sample rejection capability, outputting empty text when the target speaker is absent from the mixed speech. Additionally, Xiaomi-CocktailASR-1 supports a Chain-of-Thought (CoT) reasoning mode to provide explicit reasoning steps. Extensive experiments on various synthetic and real-world multispeaker benchmarks demonstrate that Xiaomi-CocktailASR-1 achieves state-of-the-art performance, effectively addressing the cocktail party problem through a unified architecture that balances multispeaker and single-speaker recognition accuracy, along with rejection capability.

cs.SD↗
arXiv2026

EConv-TasNet: Efficient Conv-TasNet for Effective Speech Separation

Conv-TasNet has served as a strong baseline for time-domain speech separation, and many studies have extended it with advanced architectures such as dual-path networks, U-Nets, and attention mechanisms. However, these methods often introduce high computational cost and complexity, limiting their deployment in resource-constrained scenarios. To address this issue, we propose eConv-TasNet, an efficient variant of Conv-TasNet that improves both effectiveness and efficiency without relying on resource-intensive modules. The proposed model consists of a group-wise early-splitting (GES) module and a multi-group feature aggregation (MGFA) module. GES generates discriminative speaker embeddings at intermediate stages, while MGFA progressively aggregates these group-level representations for refined mask estimation. Experimental results show that eConv-TasNet reduces model size by 22.4%, accelerates inference by 18.9%, and improves SI-SNRi by 14.0%-28.0% across three public benchmarks. Moreover, it achieves competitive performance compared with state-of-the-art methods while requiring significantly fewer parameters and lower inference cost. These results demonstrate a favorable efficiency-effectiveness trade-off for edge deployment.

cs.SD↗