Signal

Is there accompany music in the Dali or Dsing30 dataset?

1

Hi! I try the pdaugment in my accompanied mandarin song dataset, the ratio between training data and augmented data is 1.3:1, but the test accurracy reduces a little bit comparing...

编程、java等技术部分的整理都404了

请问MIR领域内有常用的数据增强（data augment）方法吗？

2

hi Beici， 看完“无痛入门系列”以及听完小宇宙那期采访，我目前也开始做音频&MIR相关的工作了。 想请问您，目前在MIR领域内有哪些常用的数据增强手段？类似于SpecAugment、RandAugment等，主要用来对原始数据进行增强，使得模型的性能和鲁棒性加强。我google大概搜了一下，发现MIR主题内的augment牵涉的不多，不知道我是不是没有找对地方。 对此，您有什么建议？比如可以去哪些顶会或期刊，搜索关键词等。谢谢

videocr_PaddleOCR.ipynb 跑demo遇到的错误

1

`from videocr import save_subtitles_to_file #@title OCR parameters input_file_path = "example_cropped.mp4" #@param {type:"string"} output_file_path = "example.srt" #@param {type:"string"} language_code = "ch" #@param {type:"string"} use_gpu = False #@param {type:"boolean"} start_time = "00:00"...

语音领域收录建议

12

https://www.isca-archive.org/

Recommendations for use with large amounts of unstructured data (e.g., audio and video)

1

Great project! I would like to use this project to manage a lot of unstructured data, any special suggestions? Data has been downloaded and exists on S3. Thanks for any...

不是音频科班，看到语音信号基础章节说过零率是频域特性，确定吗

Russian text Unicode error

1

Great work, but I encountered an error when extracting entities from mixed Russian and English text. The core error line is as follows: File "D:\project\07-multilan\langextract_example.py", line 43, in lx.io.save_annotated_documents([result], output_name="extraction_results.jsonl")...