中文
相关论文

相关论文: UNet-Based Fusion and Exponential Moving Average A…

200 篇论文

Background noise is a well-known factor that deteriorates the accuracy and reliability of speaker verification (SV) systems by blurring speech intelligibility. Various studies have used separate pretrained enhancement models as the…

音频与语音处理 · 电气工程与系统科学 2022-06-28 Ju-ho Kim , Jungwoo Heo , Hye-jin Shim , Ha-Jin Yu

In this study, we present an approach to train a single speech enhancement network that can perform both personalized and non-personalized speech enhancement. This is achieved by incorporating a frame-wise conditioning input that specifies…

音频与语音处理 · 电气工程与系统科学 2023-02-24 Zhepei Wang , Ritwik Giri , Devansh Shah , Jean-Marc Valin , Michael M. Goodwin , Paris Smaragdis

Audio-visual speech enhancement system is regarded to be one of promising solutions for isolating and enhancing speech of desired speaker. Conventional methods focus on predicting clean speech spectrum via a naive convolution neural network…

音频与语音处理 · 电气工程与系统科学 2022-09-28 Xinmeng Xu , Jianjun Hao

In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…

计算与语言 · 计算机科学 2020-05-25 Yanpei Shi , Qiang Huang , Thomas Hain

Multi-speaker speech recognition has been one of the keychallenges in conversation transcription as it breaks the singleactive speaker assumption employed by most state-of-the-artspeech recognition systems. Speech separation is consideredas…

音频与语音处理 · 电气工程与系统科学 2020-09-08 Jian Wu , Zhuo Chen , Jinyu Li , Takuya Yoshioka , Zhili Tan , Ed Lin , Yi Luo , Lei Xie

We propose an interpretable Batch-EM Unfolded Network for robust speaker localization. By embedding the iterative EM procedure within an encoder-EM-decoder architecture, the method mitigates initialization sensitivity and improves…

音频与语音处理 · 电气工程与系统科学 2026-03-18 Rina Veler , Sharon Gannot

Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and…

音频与语音处理 · 电气工程与系统科学 2025-06-16 Xingwei Sun , Heinrich Dinkel , Yadong Niu , Linzhang Wang , Junbo Zhang , Jian Luan

Despite the significant improvements in speaker recognition enabled by deep neural networks, unsatisfactory performance persists under noisy environments. In this paper, we train the speaker embedding network to learn the "clean" embedding…

音频与语音处理 · 电气工程与系统科学 2020-02-14 Danwei Cai , Weicheng Cai , Ming Li

We address the problem of speech enhancement generalisation to unseen environments by performing two manipulations. First, we embed an additional recording from the environment alone, and use this embedding to alter activations in the main…

音频与语音处理 · 电气工程与系统科学 2018-10-31 Gil Keren , Jing Han , Björn Schuller

We propose a multi-stage framework for universal speech enhancement, designed for the Interspeech 2025 URGENT Challenge. Our system first employs a Sparse Compression Network to robustly separate sources and extract an initial clean speech…

声音 · 计算机科学 2025-06-03 Nabarun Goswami , Tatsuya Harada

Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability.…

声音 · 计算机科学 2022-11-24 Hung-Shin Lee , Pin-Yuan Chen , Yao-Fei Cheng , Yu Tsao , Hsin-Min Wang

Personalized speech enhancement (PSE) methods typically rely on pre-trained speaker verification models or self-designed speaker encoders to extract target speaker clues, guiding the PSE model in isolating the desired speech. However, these…

音频与语音处理 · 电气工程与系统科学 2025-01-22 Ziling Huang , Haixin Guan , Haoran Wei , Yanhua Long

Recent advancements in speaker verification techniques show promise, but their performance often deteriorates significantly in challenging acoustic environments. Although speech enhancement methods can improve perceived audio quality, they…

音频与语音处理 · 电气工程与系统科学 2025-08-27 Adam Katav , Yair Moshe , Israel Cohen

An utterance-level speaker embedding is typically obtained by aggregating a sequence of frame-level representations. However, in real-world scenarios, individual frames encode not only speaker-relevant information but also various nuisance…

声音 · 计算机科学 2026-03-25 Junjie Li , Kong Aik Lee

Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction. This is due to the difficulty of estimating the phase of…

声音 · 计算机科学 2019-04-03 Hyeong-Seok Choi , Jang-Hyun Kim , Jaesung Huh , Adrian Kim , Jung-Woo Ha , Kyogu Lee

Modern speaker verification models use deep neural networks to encode utterance audio into discriminative embedding vectors. During the training process, these networks are typically optimized to differentiate arbitrary speakers. This…

音频与语音处理 · 电气工程与系统科学 2024-02-09 Hua Shen , Yuguang Yang , Guoli Sun , Ryan Langman , Eunjung Han , Jasha Droppo , Andreas Stolcke

We study diffusion-based speech enhancement using a Schrodinger bridge formulation and extend the EDM2 framework to this setting. We employ time-dependent preconditioning of network inputs and outputs to stabilize training and explore two…

音频与语音处理 · 电气工程与系统科学 2026-01-30 Julius Richter , Danilo de Oliveira , Timo Gerkmann

Neural multi-channel speech enhancement models, in particular those based on the U-Net architecture, demonstrate promising performance and generalization potential. These models typically encode input channels independently, and integrate…

声音 · 计算机科学 2024-10-08 Ibrahim Aldarmaki , Thamar Solorio , Bhiksha Raj , Hanan Aldarmaki

Noise-robust speaker verification leverages joint learning of speech enhancement (SE) and speaker verification (SV) to improve robustness. However, prevailing approaches rely on implicit noise suppression, which struggles to separate noise…

音频与语音处理 · 电气工程与系统科学 2025-08-12 Minu Kim , Kangwook Jang , Hoirin Kim

Online Speech Enhancement was mainly reserved for predictive models. A key advantage of these models is that for an incoming signal frame from a stream of data, the model is called only once for enhancement. In contrast, generative Speech…

音频与语音处理 · 电气工程与系统科学 2025-10-22 Bunlong Lay , Rostislav Makarov , Simon Welker , Maris Hillemann , Timo Gerkmann
‹ 上一页 1 2 3 10 下一页 ›