检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

6 篇 会议

馆藏范围

6 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

6 篇 工学
- 5 篇 电气工程
- 5 篇 计算机科学与技术...
- 2 篇 信息与通信工程
- 2 篇 软件工程
- 1 篇 电子科学与技术（可...
- 1 篇 控制科学与工程
3 篇 理学
- 3 篇 物理学
2 篇 医学
- 2 篇 临床医学

主题

6 篇 neural audio cod...
2 篇 packet loss conc...
2 篇 vector quantizat...
1 篇 subjective test
1 篇 karhunen-loeve t...
1 篇 error resilience
1 篇 real-time commun...
1 篇 speech enhanceme...
1 篇 bitrate scalable
1 篇 speech and audio...
1 篇 latent space
1 篇 real-time commun...
1 篇 conditional flow...
1 篇 low bit rate cod...

机构

3 篇 commun univ chin...
3 篇 microsoft res as...
1 篇 orange innovat i...
1 篇 univ rennes iris...
1 篇 international au...
1 篇 fraunhofer iis e...
1 篇 orange innovat l...
1 篇 univ rennes iris...
1 篇 msra peoples r c...
1 篇 orange innovat r...

作者

3 篇 xue huaying
3 篇 jiang xue
3 篇 lu yan
3 篇 peng xiulian
2 篇 zhang yuan
2 篇 philippe pierric...
2 篇 scalart pascal
2 篇 muller thomas
1 篇 zheng chengyu
1 篇 pia nicola
1 篇 multrus markus
1 篇 gros laetitia
1 篇 strauss martin
1 篇 ragot stephane
1 篇 edler bernd
1 篇 ragoti stephane

语言

6 篇 英文

检索条件"主题词=neural audio coding"

共 6 条记录，以下是1-10 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Post-Training Latent Dimension Reduction in neural audio coding 32

Post-Training Latent Dimension Reduction in Neural Audio Cod...

引用

32nd European Signal Processing Conference (EUSIPCO)

作者： Muller, Thomas Ragot, Stephane Philippe, Pierrick Scalart, Pascal Orange Innovat Lannion France Univ Rennes IRISA Lannion France Orange Innovat Rennes France

ISBN: (纸本)9789464593617;9798331519773

This work addresses the problem of latent space quantization in neural audio coding. A covariance analysis of latent space is performed on several pre-trained audio coding models (Lyra V2, EnCodec, audioDec). It is proposed to truncate latent space dimension using a fixed linear transform. The Karhunen-Loeve transform (KLT) is applied on learned residual vector quantization (RVQ) codebooks. The proposed method is applied in a backward-compatible way to EnCodec, and we show that quantization complexity and codebook storage are reduced (by 43.4%), with no noticeable difference in subjective AB tests.

关键词： neural audio coding vector quantization latent space Karhunen-Loeve transform

来源：评论

学校读者我要写书评

暂无评论

FlowMAC: Conditional Flow Matching for audio coding at Low Bit Rates

FlowMAC: Conditional Flow Matching for Audio Coding at Low B...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Pia, Nicola Strauss, Martin Multrus, Markus Edler, Bernd Fraunhofer IIS Erlangen Germany International Audio Laboratories Erlangen Erlangen Germany

ISBN: (纸本)9798350368741

This paper introduces FlowMAC, a novel neural audio codec for high-quality general audio compression at low bit rates based on conditional flow matching (CFM). FlowMAC jointly learns a mel spectrogram encoder, quantizer and decoder. At inference time the decoder integrates a continuous normalizing flow via an ODE solver to generate a high-quality mel spectrogram. This is the first time that a CFM-based approach is applied to general audio coding, enabling a scalable, simple and memory efficient training. Our subjective evaluations show that FlowMAC at 3 kbps achieves similar quality as state-of-the-art GAN-based and DDPM-based neural audio codecs at double the bit rate. Moreover, FlowMAC offers a tunable inference pipeline, which permits to trade off complexity and quality. This enables real-time coding on CPU, while maintaining high perceptual quality. © 2025 IEEE.

关键词： conditional flow matching low bit rate coding neural audio coding

来源：评论

学校读者我要写书评

暂无评论

Towards Error-Resilient neural Speech coding 23

Towards Error-Resilient Neural Speech Coding

引用

Interspeech Conference

作者： Xue, Huaying Peng, Xiulian Jiang, Xue Lu, Yan Microsoft Res Asia Beijing Peoples R China Commun Univ China Beijing Peoples R China

neural audio coding has shown very promising results recently in the literature to largely outperform traditional codecs but limited attention has been paid on its error resilience. neural codecs trained considering only source coding tend to be extremely sensitive to channel noises, especially in wireless channels with high error rate. In this paper, we investigate how to elevate the error resilience of neural audio codecs for packet losses that often occur during real-time communications. We propose a feature-domain packet loss concealment algorithm (FD-PLC) for real-time neural speech coding. Specifically, we introduce a self-attention-based module on the received latent features to recover lost frames in the feature domain before the decoder. A hybrid segment-level and frame-level frequency-domain discriminator is employed to guide the network to focus on both the generative quality of lost frames and the continuity with neighbouring frames. Experimental results on several error patterns show that the proposed scheme can achieve better robustness compared with the corresponding error-free and error-resilient baselines. We also show that feature-domain concealment is superior to waveform-domain counterpart as post-processing.

关键词： error resilience packet loss concealment neural audio coding real-time communication

来源：评论

学校读者我要写书评

暂无评论

Cross-Scale Vector Quantization for Scalable neural Speech coding 23

Cross-Scale Vector Quantization for Scalable Neural Speech C...

引用

Interspeech Conference

作者： Jiang, Xue Peng, Xiulian Xue, Huaying Zhang, Yuan Lu, Yan Commun Univ China Beijing Peoples R China Microsoft Res Asia Beijing Peoples R China MSRA Beijing Peoples R China

Bitrate scalability is a desirable feature for audio coding in real-time communications. Existing neural audio codecs usually enforce a specific bitrate during training, so different models need to be trained for each target bitrate, which increases the memory footprint at the sender and the receiver side and transcoding is often needed to support multiple receivers. In this paper, we introduce a cross-scale scalable vector quantization scheme (CSVQ), in which multi-scale features are encoded progressively with stepwise feature fusion and refinement. In this way, a coarse-level signal is reconstructed if only a portion of the bitstream is received, and progressively improves the quality as more bits are available. The proposed CSVQ scheme can be flexibly applied to any neural audio coding network with a mirrored auto-encoder structure to achieve bitrate scalability. Subjective results show that the proposed scheme outperforms the classical residual VQ (RVQ) with scalability. Moreover, the proposed CSVQ at 3 kbps outperforms Opus at 9 kbps and Lyra at 3kbps and it could provide a graceful quality boost with bitrate increase.

关键词： neural audio coding bitrate scalable vector quantization

来源：评论

学校读者我要写书评

暂无评论

Speech quality evaluation of neural audio codecs 25

Speech quality evaluation of neural audio codecs

引用

25th Interspeech Conference

作者： Muller, Thomas Ragoti, Stephane Gros, Laetitia Philippe, Pierrick Scalart, Pascal Orange Innovat Ile De France France Univ Rennes IRISA Rennes France

This paper presents speech quality results to characterize the state of the art and technological advance of recent neural audio codecs targeting low bitrates. audio quality was evaluated in one clean speech experiment (in French). Degradation Mean Opinion Score (DMOS) results are reported and discussed for neural audio codecs (LPCNet, Lyra V2, EnCodec, audioCraft, audioDec, Descript audio Codec) - traditional codecs (Opus, EVS) are also included as performance yardsticks. We also discuss observed codec complexity to complement subjective test results.

关键词： speech and audio coding subjective test neural audio coding

来源：评论

学校读者我要写书评

暂无评论

END-TO-END neural SPEECH coding FOR REAL-TIME COMMUNICATIONS 47

END-TO-END NEURAL SPEECH CODING FOR REAL-TIME COMMUNICATIONS

引用

47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Jiang, Xue Peng, Xiulian Zheng, Chengyu Xue, Huaying Zhang, Yuan Lu, Yan Commun Univ China Beijing Peoples R China Microsoft Res Asia Beijing Peoples R China

ISBN: (纸本)9781665405409

Deep-learning based methods have shown their advantages in audio coding over traditional ones but limited attention has been paid on real-time communications (RTC). This paper proposes the TFNet, an end-to-end neural speech codec with low latency for RTC. It takes an encoder-temporal filtering-decoder paradigm that has seldom been investigated in audio coding. An interleaved structure is proposed for temporal filtering to capture both short-term and long-term temporal dependencies. Furthermore, with end-to-end optimization, the TFNet is jointly optimized with speech enhancement and packet loss concealment, yielding a one-for-all network for three tasks. Both subjective and objective results demonstrate the efficiency of the proposed TFNet.

关键词： neural audio coding real-time communications speech enhancement packet loss concealment

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共1页 << < 1 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：