Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 1602.08185

Extension spectrale d'un signal de parole de la bande t\'el\'ephonique \`a la bande AM

Jean-Marc Valin
View original source ↗Read source document ↗Export metadata ↓

Abstract

This document proposes a bandwidth extension system producing a wideband signal from a narrowband speech signal. The extension is performed independently for high and low frequencies. High-frequency extension uses the excitation-filter model. Extension of the excitation is performed in the time domain using a non-linear function, while the spectral envelope is extended in the cepstral domain using a multi-layer perceptron. Low-band extension is based on the sinusoidal model. The amplitude of sinusoids is also estimated using a multi-layer perceptron. The results show that the sound quality after extension is higher than that of narrowband speech, with a significant variation across listeners. Some of the techniques, including excitation extension, are of interest in the field of speech coding. ----- Le pr\'esent m\'emoire propose un syst\`eme d'extension de la bande permettant de produire un signal en bande AM \`a partir d'un signal de parole en bande t\'el\'ephonique. L'extension est effectu\'ee de fa\c{c}on ind\'ependante pour les hautes fr\'equences et les basses fr\'equences. L'extension des hautes fr\'equences utilise le mod\`ele filtre-excitation. L'extension de l'excitation est r\'ealis\'ee dans le domaine temporel par une fonction non lin\'eaire, alors que l'extension de l'enveloppe spectrale s'effectue dans le domaine cepstral par un perceptron multi-couches. L'extension de la bande basse utilise le mod\`ele sinuso\"idal. L'amplitude des sinuso\"ides est aussi estim\'ee par un perceptron multi-couches. Les r\'esultats obtenus montrent que la qualit\'e sonore apr\`es extension est sup\'erieure \`a celle de la bande t\'el\'ephonique, avec une importante diff\'erence entre les auditeurs. Certaines techniques d\'evelopp\'ees, dont l'extension de l'excitation, pr\'esentent un certain int\'er\^et pour le domaine du codage de la parole.

Explore related subjects

cs.SDcs.MM

Keep this discovery

BibTeXRIS

Jean-Marc Valin. 2016-02-26. Extension spectrale d'un signal de parole de la bande t\'el\'ephonique \`a la bande AM. https://arxiv.org/abs/1602.08185

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↗