中文
相关论文

相关论文: Real-time Streaming Wave-U-Net with Temporal Convo…

200 篇论文

This paper proposes a speech enhancement method which exploits the high potential of residual connections in a Wide Residual Network architecture. This is supported on single dimensional convolutions computed alongside the time domain,…

音频与语音处理 · 电气工程与系统科学 2019-04-11 Jorge Llombart , Dayana Ribas , Antonio Miguel , Luis Vicente , Alfonso Ortega , Eduardo Lleida

Multi-stage learning is an effective technique to invoke multiple deep-learning modules sequentially. This paper applies multi-stage learning to speech enhancement by using a multi-stage structure, where each stage comprises a…

音频与语音处理 · 电气工程与系统科学 2021-02-25 Ju Lin , Adriaan J. van Wijngaarden , Kuang-Ching Wang , Melissa C. Smith

In this paper, we present a novel two-pass approach to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model. Our model adopts the hybrid CTC/attention architecture, in which the conformer layers in the…

声音 · 计算机科学 2021-12-30 Binbin Zhang , Di Wu , Zhuoyuan Yao , Xiong Wang , Fan Yu , Chao Yang , Liyong Guo , Yaguang Hu , Lei Xie , Xin Lei

Deep learning-based speech enhancement has seen huge improvements and recently also expanded to full band audio (48 kHz). However, many approaches have a rather high computational complexity and require big temporal buffers for real time…

音频与语音处理 · 电气工程与系统科学 2022-05-12 Hendrik Schröter , Alberto N. Escalante-B. , Tobias Rosenkranz , Andreas Maier

Multi-frame algorithms for single-channel speech enhancement are able to take advantage from short-time correlations within the speech signal. Deep Filtering (DF) was proposed to directly estimate a complex filter in frequency domain to…

音频与语音处理 · 电气工程与系统科学 2023-05-16 Hendrik Schröter , Tobias Rosenkranz , Alberto N. Escalante-B. , Andreas Maier

An inferior performance of the streaming automatic speech recognition models versus non-streaming model is frequently seen due to the absence of future context. In order to improve the performance of the streaming model and reduce the…

声音 · 计算机科学 2022-03-30 Jingyu Sun , Guiping Zhong , Dinghao Zhou , Baoxiang Li

Studies have shown that in noisy acoustic environments, providing binaural signals to the user of an assistive listening device may improve speech intelligibility and spatial awareness. This paper presents a binaural speech enhancement…

音频与语音处理 · 电气工程与系统科学 2024-03-11 Vikas Tokala , Eric Grinstein , Mike Brookes , Simon Doclo , Jesper Jensen , Patrick A. Naylor

The reliability of using fully convolutional networks (FCNs) has been successfully demonstrated by recent studies in many speech applications. One of the most popular variants of these FCNs is the `U-Net', which is an encoder-decoder…

音频与语音处理 · 电气工程与系统科学 2021-11-10 Vinay Kothapally , Wei Xia , Shahram Ghorbani , John H. L. Hansen , Wei Xue , Jing Huang

Most video restoration networks are slow, have high computational load, and can't be used for real-time video enhancement. In this work, we design an efficient and fast framework to perform real-time video enhancement for practical…

计算机视觉与模式识别 · 计算机科学 2023-03-24 Jeya Maria Jose Valanarasu , Rahul Garg , Andeep Toor , Xin Tong , Weijuan Xi , Andreas Lugmayr , Vishal M. Patel , Anne Menini

State-of-the-art text-independent speaker verification systems typically use cepstral features or filter bank energies as speech features. Recent studies attempted to extract speaker embeddings directly from raw waveforms and have shown…

音频与语音处理 · 电气工程与系统科学 2021-06-10 Ge Zhu , Fei Jiang , Zhiyao Duan

In recent years, many deep learning techniques for single-channel sound source separation have been proposed using recurrent, convolutional and transformer networks. When multiple microphones are available, spatial diversity between…

音频与语音处理 · 电气工程与系统科学 2022-08-23 Ali Aroudi , Stefan Uhlich , Marc Ferras Font

This paper introduces a convolutional recurrent network with attention for speech command recognition. Attention models are powerful tools to improve performance on natural language, image captioning and speech tasks. The proposed model…

音频与语音处理 · 电气工程与系统科学 2018-08-28 Douglas Coimbra de Andrade , Sabato Leo , Martin Loesener Da Silva Viana , Christoph Bernkopf

While speech recognition Word Error Rate (WER) has reached human parity for English, continuous speech recognition scenarios such as voice typing and meeting transcriptions still suffer from segmentation and punctuation problems, resulting…

计算与语言 · 计算机科学 2023-01-11 Piyush Behre , Sharman Tan , Padma Varadharajan , Shuangyu Chang

Environmental sound classification systems often do not perform robustly across different sound classification tasks and audio signals of varying temporal structures. We introduce a multi-stream convolutional neural network with temporal…

声音 · 计算机科学 2019-01-28 Xinyu Li , Venkata Chebiyyam , Katrin Kirchhoff

Real-time speech synthesis requires balancing inference latency and acoustic fidelity for interactive applications. Conventional continuous text-to-speech pipelines require computationally intensive neural vocoders to reconstruct phase…

音频与语音处理 · 电气工程与系统科学 2026-04-15 Tianhui Su , Tien-Ping Tan , Salima Mdhaffar , Yannick Estève , Aghilas Sini

Convolutional neural networks (CNNs) with dilated filters such as the Wavenet or the Temporal Convolutional Network (TCN) have shown good results in a variety of sequence modelling tasks. However, efficiently modelling long-term…

机器学习 · 计算机科学 2019-11-18 Daniel Stoller , Mi Tian , Sebastian Ewert , Simon Dixon

Recent speech enhancement methods based on convolutional neural networks (CNNs) and transformer have been demonstrated to efficaciously capture time-frequency (T-F) information on spectrogram. However, the correlation of each channels of…

声音 · 计算机科学 2024-07-16 Jizhen Li , Xinmeng Xu , Weiping Tu , Yuhong Yang , Rong Zhu

In this contribution, we present a novel online approach to multichannel speech enhancement. The proposed method estimates the enhanced signal through a filter-and-sum framework. More specifically, complex-valued masks are estimated by a…

音频与语音处理 · 电气工程与系统科学 2021-08-09 Mhd Modar Halimeh , Walter Kellermann

Recent advancements in discrete token-based speech generation have highlighted the importance of token-to-waveform generation for audio quality, particularly in real-time interactions. Traditional frameworks integrating semantic tokens with…

声音 · 计算机科学 2025-07-02 Dake Guo , Jixun Yao , Linhan Ma , He Wang , Lei Xie

In this paper, we propose a multi-channel network for simultaneous speech dereverberation, enhancement and separation (DESNet). To enable gradient propagation and joint optimization, we adopt the attentional selection mechanism of the…

声音 · 计算机科学 2020-11-17 Yihui Fu , Jian Wu , Yanxin Hu , Mengtao Xing , Lei Xie