自定义博客皮肤VIP专享

*博客头图:

格式为PNG、JPG,宽度*高度大于1920*100像素,不超过2MB,主视觉建议放在右侧,请参照线上博客头图

请上传大于1920*100像素的图片!

博客底图:

图片格式为PNG、JPG,不超过1MB,可上下左右平铺至整个背景

栏目图:

图片格式为PNG、JPG,图片宽度*高度为300*38像素,不超过0.5MB

主标题颜色:

RGB颜色,例如:#AFAFAF

Hover:

RGB颜色,例如:#AFAFAF

副标题颜色:

RGB颜色,例如:#AFAFAF

自定义博客皮肤

-+
  • 博客(7)
  • 资源 (1)
  • 收藏
  • 关注

原创 【PaperReading】AN ATTENTION-BASED NEURAL NETWORK APPROACH FOR SINGLE CHANNEL SPEECH ENHANCEMENT

Title:AN ATTENTION-BASED NEURAL NETWORK APPROACH FOR SINGLE CHANNEL SPEECH ENHANCEMENTWhat’s main claim? Key idea?​ In this paper, the authors explore the attention-based neural network structures for improving the performance of speech enhancement. T

2020-10-26 17:25:18 305

原创 【PaperReading】DUAL-PATH RNN: EFFICIENT LONG SEQUENCE MODELING FOR TIME-DOMAIN SINGLE-CHANNEL SPEECH

Title:DUAL-PATH RNN: EFFICIENT LONG SEQUENCE MODELING FOR TIME-DOMAIN SINGLE-CHANNEL SPEECH SEPARATIONWhat’s main claim? Key idea?This paper proposes a simple network called dual-path RNN (DPRNN), that organizes any kinds of RNN layers to model long se

2020-10-26 17:23:09 532

原创 【PaperReading】T-GSA: TRANSFORMER WITH GAUSSIAN-WEIGHTED SELF-ATTENTION FOR SPEECH ENHANCEMENT

Title:T-GSA: TRANSFORMER WITH GAUSSIAN-WEIGHTED SELF-ATTENTION FOR SPEECH ENHANCEMENTWhat’s main claim? Key idea?This paper introduces a self-supervised speech pre-training method called TERA. The authors use a multi-target auxiliary task to pre-train

2020-10-26 17:21:53 590 1

原创 【PaperReading】TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech

Title:TERA: Self-Supervised Learning of Transformer Encoder Representation for SpeechWhat’s main claim? Key idea?This paper introduces a self-supervised speech pre-training method called TERA. The authors use a multi-target auxiliary task to pre-train

2020-10-26 17:17:15 455

原创 【PaperReading】Attention Is All You Need

Paper:Title:Attention Is All You NeedWhat’s main claim? Key idea?​ This paper proposed a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.Is the idea neat?

2020-10-26 17:12:41 214

原创 【PaperReading】SPEAKERFILTER: DEEP LEARNING-BASED TARGET SPEAKER EXTRACTION USING ANCHOR SPEECH

Title: SPEAKERFILTER: DEEP LEARNING-BASED TARGET SPEAKER EXTRACTION USING ANCHOR SPEECHWhat’s main claim? Key idea?This paper proposed a novel framework for target speaker separation with anchor speech (Speakerfilter). In the framework, They use a conv

2020-10-26 17:11:26 325

原创 论文十二问(You are how you read)

论文十二问:What’s main claim? Key idea?What’s key limitation?Is there code available? Data?Is the idea neat? Is it counter-intuitive?Is the contribution significant enough?Is the experimentation good? Manual tuning?Are there important related papers I m

2020-10-05 11:31:43 331

sbc-1.4.zip

蓝牙音频协议中的sbc协议的官方源码,版本为sbc-1.4版本。c语音。 编译运行:./configure --prefix=/usr --disable-static --disable-tester && make

2020-06-15

空空如也

TA创建的收藏夹 TA关注的收藏夹

TA关注的人

提示
确定要删除当前文章?
取消 删除