Výsledky vyhledávání

Report

Outlier-aware Inlier Modeling and Multi-scale Scoring for Anomalous Sound Detection via Multitask Learning

Autor: Zhang, Yucong, Suo, Hongbin, Wan, Yulong, Li, Ming

This paper proposes an approach for anomalous sound detection that incorporates outlier exposure and inlier modeling within a unified framework by multitask learning. While outlier exposure-based methods can extract features efficiently, it is not ro

Externí odkaz: http://arxiv.org/abs/2309.07500

Zobrazit plný text záznamu

Report

Task-Agnostic Structured Pruning of Speech Representation Models

Autor: Wang, Haoyu, Wang, Siyuan, Zhang, Wei-Qiang, Suo, Hongbin, Wan, Yulong

Self-supervised pre-trained models such as Wav2vec2, Hubert, and WavLM have been shown to significantly improve many speech tasks. However, their large memory and strong computational requirements hinder their industrial applicability. Structured pru

Externí odkaz: http://arxiv.org/abs/2306.01385

Zobrazit plný text záznamu

Report

Multilingual Zero Resource Speech Recognition Base on Self-Supervise Pre-Trained Acoustic Models

Autor: Wang, Haoyu, Zhang, Wei-Qiang, Suo, Hongbin, Wan, Yulong

Labeled audio data is insufficient to build satisfying speech recognition systems for most of the languages in the world. There have been some zero-resource methods trying to perform phoneme or word-level speech recognition without labeled audio data

Externí odkaz: http://arxiv.org/abs/2210.06936

Zobrazit plný text záznamu

Report

Simultaneous Speech Extraction for Multiple Target Speakers under the Meeting Scenarios

Autor: Zeng, Bang, Suo, Hongbing, Wan, Yulong, Li, Ming

The common target speech separation directly estimate the target source, ignoring the interrelationship between different speakers at each frame. We propose a multiple-target speech separation model (MTSS) to simultaneously extract each speaker's voi

Externí odkaz: http://arxiv.org/abs/2206.08525

Zobrazit plný text záznamu