🕷️ Crawler Inspector

URL Lookup

Direct Parameter Lookup

Raw Queries and Responses

1. Shard Calculation

Query:

Response:

Calculated Shard: 61 (from laksa060)

2. Crawled Status Check

Query:

curl -X POST \
  'http://laksa061.int.ahrefs:8124/' \
  -H 'Content-Type: text/plain' \
  -H 'X-ClickHouse-Database: crawler3' \
  -H 'Authorization: Basic YXBpOg==' \
  -d 'SELECT getAhrefsURLFromUnparsed(src_unparsed) AS found_url, ifNull(toUnixTimestamp(download_stamp), 0) AS crawl_time, ifNull(toUnixTimestamp(props_url_first_seen), 0) AS first_indexed_time, download_http_code AS http_code, src_unparsed AS src_unparsed, src_root_hash AS src_root_hash, history_drop_reason AS history_drop_reason, meta_title AS meta_title, meta_descriptions AS meta_descriptions, attrs_boilerpipe_text AS attrs_boilerpipe_text, attrs_markdown AS attrs_markdown, attrs_readable_markdown AS attrs_readable_markdown, meta_canonical AS meta_canonical FROM crawler3.page_info_local FINAL PREWHERE (src_root_hash, src_unparsed) IN ((getAhrefsRootHashFromUnparsed(getAhrefsUnparsedNoserviceFromURL(\'https://papers.cool/arxiv/2509.07756\')), getAhrefsUnparsedNoserviceFromURL(\'https://papers.cool/arxiv/2509.07756\'))) FORMAT JSONEachRow'

Response:

{"found_url":"https:\/\/papers.cool\/arxiv\/2509.07756","crawl_time":1776186293,"first_indexed_time":1757597615,"http_code":200,"src_unparsed":"cool,papers!\/arxiv\/2509.07756 s443","src_root_hash":"17309916099783778261","history_drop_reason":null,"meta_title":"Spectral and Rhythm Feature Performance Evaluation for Category and Class Level Audio Classification with Deep Convolutional Neural Networks | Cool Papers - Immersive Paper Discovery","meta_descriptions":["Next to decision tree and k-nearest neighbours algorithms deep convolutional neural networks (CNNs) are widely used to classify audio data in many domains like music, speech or environmental sounds. To train a specific CNN various spectral and rhythm features like mel-scaled spectrograms, mel-frequency cepstral coefficients (MFCC), cyclic tempograms, short-time Fourier transform (STFT) chromagrams, constant-Q transform (CQT) chromagrams and chroma energy normalized statistics (CENS) chromagrams can be used as digital image input data for the neural network. The performance of these spectral and rhythm features for audio category level as well as audio class level classification is investigated in detail with a deep CNN and the ESC-50 dataset with 2,000 labeled environmental audio recordings using an end-to-end deep learning pipeline. The evaluated metrics accuracy, precision, recall and F1 score for multiclass classification clearly show that the mel-scaled spectrograms and the mel-frequency cepstral coefficients (MFCC) perform significantly better then the other spectral and rhythm features investigated in this research for audio classification tasks using deep CNNs."],"attrs_boilerpipe_text":"Next to decision tree and k-nearest neighbours algorithms deep convolutional neural networks (CNNs) are widely used to classify audio data in many domains like music, speech or environmental sounds. To train a specific CNN various spectral and rhythm features like mel-scaled spectrograms, mel-frequency cepstral coefficients (MFCC), cyclic tempograms, short-time Fourier transform (STFT) chromagrams, constant-Q transform (CQT) chromagrams and chroma energy normalized statistics (CENS) chromagrams can be used as digital image input data for the neural network. The performance of these spectral and rhythm features for audio category level as well as audio class level classification is investigated in detail with a deep CNN and the ESC-50 dataset with 2,000 labeled environmental audio recordings using an end-to-end deep learning pipeline. The evaluated metrics accuracy, precision, recall and F1 score for multiclass classification clearly show that the mel-scaled spectrograms and the mel-frequency cepstral coefficients (MFCC) perform significantly better then the other spectral and rhythm features investigated in this research for audio classification tasks using deep CNNs.\nSubjects\n:\nSound\n,\nArtificial Intelligence\n,\nComputer Vision and Pattern Recognition\n,\nMachine Learning\n,\nAudio and Speech Processing\nPublish\n:\n2025-09-09 13:54:41 UTC","attrs_markdown":"# 2509\\.07756\nTotal: 1\n\n## [\\#1](https:\/\/arxiv.org\/abs\/2509.07756 \"1\/1\") [Spectral and Rhythm Feature Performance Evaluation for Category and Class Level Audio Classification with Deep Convolutional Neural Networks](https:\/\/papers.cool\/arxiv\/2509.07756) [\\[PDF\\]]() [\\[Copy\\]]() [\\[Kimi1\\]]() [\\[REL\\]]()\n**Author**: [Friedrich Wolf-Monheim](https:\/\/arxiv.org\/search\/?searchtype=author&query=Friedrich%20Wolf-Monheim)\n\nNext to decision tree and k-nearest neighbours algorithms deep convolutional neural networks (CNNs) are widely used to classify audio data in many domains like music, speech or environmental sounds. To train a specific CNN various spectral and rhythm features like mel-scaled spectrograms, mel-frequency cepstral coefficients (MFCC), cyclic tempograms, short-time Fourier transform (STFT) chromagrams, constant-Q transform (CQT) chromagrams and chroma energy normalized statistics (CENS) chromagrams can be used as digital image input data for the neural network. The performance of these spectral and rhythm features for audio category level as well as audio class level classification is investigated in detail with a deep CNN and the ESC-50 dataset with 2,000 labeled environmental audio recordings using an end-to-end deep learning pipeline. The evaluated metrics accuracy, precision, recall and F1 score for multiclass classification clearly show that the mel-scaled spectrograms and the mel-frequency cepstral coefficients (MFCC) perform significantly better then the other spectral and rhythm features investigated in this research for audio classification tasks using deep CNNs.\n\n**Subjects**:  [Sound](https:\/\/papers.cool\/arxiv\/cs.SD)   ,  [Artificial Intelligence](https:\/\/papers.cool\/arxiv\/cs.AI)   ,  [Computer Vision and Pattern Recognition](https:\/\/papers.cool\/arxiv\/cs.CV)   ,  [Machine Learning](https:\/\/papers.cool\/arxiv\/cs.LG)   ,  [Audio and Speech Processing](https:\/\/papers.cool\/arxiv\/eess.AS)\n\n**Publish**: 2025-09-09 13:54:41 UTC\n***\n\nDesigned by [kexue.fm](https:\/\/kexue.fm\/) \\| Powered by [kimi.ai](https:\/\/kimi.moonshot.cn\/?ref=papers.cool)\n\nInclude([OR](\"The logical relationship between keywords (OR\/AND)\")):\n\nExclude:\n\nSearch\n\nFilter\n\nHighlight\n\nStared Paper(s):\n\n\\#1 [Spectral and Rhythm Feature Performance Evaluation for Category and Class Level Audio Classification with Deep Convolutional Neural Networks](https:\/\/papers.cool\/arxiv\/2509.07756#2509.07756)\n\nExport\n\nMagic Token:\n\nKimi Language:\n\nDesc Language:\n\nSave\n\nBug report? Issue submit? Please visit:\n\n**Github:** <https:\/\/github.com\/bojone\/papers.cool>\n\nPlease read our [Disclaimer](https:\/\/github.com\/bojone\/papers.cool\/blob\/main\/Disclaimer\/README_en.md) before proceeding.\n\nFor more interesting features, please visit [kexue.fm](https:\/\/kexue.fm\/) and [kimi.ai](https:\/\/kimi.moonshot.cn\/?ref=papers.cool).","attrs_readable_markdown":"Next to decision tree and k-nearest neighbours algorithms deep convolutional neural networks (CNNs) are widely used to classify audio data in many domains like music, speech or environmental sounds. To train a specific CNN various spectral and rhythm features like mel-scaled spectrograms, mel-frequency cepstral coefficients (MFCC), cyclic tempograms, short-time Fourier transform (STFT) chromagrams, constant-Q transform (CQT) chromagrams and chroma energy normalized statistics (CENS) chromagrams can be used as digital image input data for the neural network. The performance of these spectral and rhythm features for audio category level as well as audio class level classification is investigated in detail with a deep CNN and the ESC-50 dataset with 2,000 labeled environmental audio recordings using an end-to-end deep learning pipeline. The evaluated metrics accuracy, precision, recall and F1 score for multiclass classification clearly show that the mel-scaled spectrograms and the mel-frequency cepstral coefficients (MFCC) perform significantly better then the other spectral and rhythm features investigated in this research for audio classification tasks using deep CNNs.\n\n**Subjects**:  [Sound](https:\/\/papers.cool\/arxiv\/cs.SD)   ,  [Artificial Intelligence](https:\/\/papers.cool\/arxiv\/cs.AI)   ,  [Computer Vision and Pattern Recognition](https:\/\/papers.cool\/arxiv\/cs.CV)   ,  [Machine Learning](https:\/\/papers.cool\/arxiv\/cs.LG)   ,  [Audio and Speech Processing](https:\/\/papers.cool\/arxiv\/eess.AS)\n\n**Publish**: 2025-09-09 13:54:41 UTC\n***","meta_canonical":null}

3. Robots.txt Check

Query:

Response:

4. Spam/Ban Check

Query:

Response:

5. Seen Status Check

ℹ️ Skipped - page is already crawled

📄

INDEXABLE

✅

CRAWLED

1 day ago

🤖

ROBOTS ALLOWED

Page Info Filters

Filter	Status	Condition	Details
HTTP status	PASS	`download_http_code = 200`	HTTP 200
Age cutoff	PASS	`download_stamp > now() - 6 MONTH`	0 months ago
History drop	PASS	`isNull(history_drop_reason)`	No drop reason
Spam/ban	PASS	`fh_dont_index != 1 AND ml_spam_score = 0`	ml_spam_score=0
Canonical	PASS	`meta_canonical IS NULL OR = '' OR = src_unparsed`	Not set

Page Details

Property	Value
URL	https://papers.cool/arxiv/2509.07756
Last Crawled	2026-04-14 17:04:53 (1 day ago)
First Indexed	2025-09-11 13:33:35 (7 months ago)
HTTP Status Code	200
Meta Title	Spectral and Rhythm Feature Performance Evaluation for Category and Class Level Audio Classification with Deep Convolutional Neural Networks \| Cool Papers - Immersive Paper Discovery
Meta Description	Next to decision tree and k-nearest neighbours algorithms deep convolutional neural networks (CNNs) are widely used to classify audio data in many domains like music, speech or environmental sounds. To train a specific CNN various spectral and rhythm features like mel-scaled spectrograms, mel-frequency cepstral coefficients (MFCC), cyclic tempograms, short-time Fourier transform (STFT) chromagrams, constant-Q transform (CQT) chromagrams and chroma energy normalized statistics (CENS) chromagrams can be used as digital image input data for the neural network. The performance of these spectral and rhythm features for audio category level as well as audio class level classification is investigated in detail with a deep CNN and the ESC-50 dataset with 2,000 labeled environmental audio recordings using an end-to-end deep learning pipeline. The evaluated metrics accuracy, precision, recall and F1 score for multiclass classification clearly show that the mel-scaled spectrograms and the mel-frequency cepstral coefficients (MFCC) perform significantly better then the other spectral and rhythm features investigated in this research for audio classification tasks using deep CNNs.
Meta Canonical	null
Boilerpipe Text	Next to decision tree and k-nearest neighbours algorithms deep convolutional neural networks (CNNs) are widely used to classify audio data in many domains like music, speech or environmental sounds. To train a specific CNN various spectral and rhythm features like mel-scaled spectrograms, mel-frequency cepstral coefficients (MFCC), cyclic tempograms, short-time Fourier transform (STFT) chromagrams, constant-Q transform (CQT) chromagrams and chroma energy normalized statistics (CENS) chromagrams can be used as digital image input data for the neural network. The performance of these spectral and rhythm features for audio category level as well as audio class level classification is investigated in detail with a deep CNN and the ESC-50 dataset with 2,000 labeled environmental audio recordings using an end-to-end deep learning pipeline. The evaluated metrics accuracy, precision, recall and F1 score for multiclass classification clearly show that the mel-scaled spectrograms and the mel-frequency cepstral coefficients (MFCC) perform significantly better then the other spectral and rhythm features investigated in this research for audio classification tasks using deep CNNs. Subjects : Sound , Artificial Intelligence , Computer Vision and Pattern Recognition , Machine Learning , Audio and Speech Processing Publish : 2025-09-09 13:54:41 UTC
Markdown	# 2509\.07756 Total: 1 ## [\#1](https://arxiv.org/abs/2509.07756 "1/1") [Spectral and Rhythm Feature Performance Evaluation for Category and Class Level Audio Classification with Deep Convolutional Neural Networks](https://papers.cool/arxiv/2509.07756) [\[PDF\]]() [\[Copy\]]() [\[Kimi1\]]() [\[REL\]]() Author: [Friedrich Wolf-Monheim](https://arxiv.org/search/?searchtype=author&query=Friedrich%20Wolf-Monheim) Next to decision tree and k-nearest neighbours algorithms deep convolutional neural networks (CNNs) are widely used to classify audio data in many domains like music, speech or environmental sounds. To train a specific CNN various spectral and rhythm features like mel-scaled spectrograms, mel-frequency cepstral coefficients (MFCC), cyclic tempograms, short-time Fourier transform (STFT) chromagrams, constant-Q transform (CQT) chromagrams and chroma energy normalized statistics (CENS) chromagrams can be used as digital image input data for the neural network. The performance of these spectral and rhythm features for audio category level as well as audio class level classification is investigated in detail with a deep CNN and the ESC-50 dataset with 2,000 labeled environmental audio recordings using an end-to-end deep learning pipeline. The evaluated metrics accuracy, precision, recall and F1 score for multiclass classification clearly show that the mel-scaled spectrograms and the mel-frequency cepstral coefficients (MFCC) perform significantly better then the other spectral and rhythm features investigated in this research for audio classification tasks using deep CNNs. Subjects: [Sound](https://papers.cool/arxiv/cs.SD) , [Artificial Intelligence](https://papers.cool/arxiv/cs.AI) , [Computer Vision and Pattern Recognition](https://papers.cool/arxiv/cs.CV) , [Machine Learning](https://papers.cool/arxiv/cs.LG) , [Audio and Speech Processing](https://papers.cool/arxiv/eess.AS) Publish: 2025-09-09 13:54:41 UTC * Designed by [kexue.fm](https://kexue.fm/) \\| Powered by [kimi.ai](https://kimi.moonshot.cn/?ref=papers.cool) Include([OR]("The logical relationship between keywords (OR/AND)")): Exclude: Search Filter Highlight Stared Paper(s): \#1 [Spectral and Rhythm Feature Performance Evaluation for Category and Class Level Audio Classification with Deep Convolutional Neural Networks](https://papers.cool/arxiv/2509.07756#2509.07756) Export Magic Token: Kimi Language: Desc Language: Save Bug report? Issue submit? Please visit: Github:** <https://github.com/bojone/papers.cool> Please read our [Disclaimer](https://github.com/bojone/papers.cool/blob/main/Disclaimer/README_en.md) before proceeding. For more interesting features, please visit [kexue.fm](https://kexue.fm/) and [kimi.ai](https://kimi.moonshot.cn/?ref=papers.cool).
Readable Markdown	Next to decision tree and k-nearest neighbours algorithms deep convolutional neural networks (CNNs) are widely used to classify audio data in many domains like music, speech or environmental sounds. To train a specific CNN various spectral and rhythm features like mel-scaled spectrograms, mel-frequency cepstral coefficients (MFCC), cyclic tempograms, short-time Fourier transform (STFT) chromagrams, constant-Q transform (CQT) chromagrams and chroma energy normalized statistics (CENS) chromagrams can be used as digital image input data for the neural network. The performance of these spectral and rhythm features for audio category level as well as audio class level classification is investigated in detail with a deep CNN and the ESC-50 dataset with 2,000 labeled environmental audio recordings using an end-to-end deep learning pipeline. The evaluated metrics accuracy, precision, recall and F1 score for multiclass classification clearly show that the mel-scaled spectrograms and the mel-frequency cepstral coefficients (MFCC) perform significantly better then the other spectral and rhythm features investigated in this research for audio classification tasks using deep CNNs. Subjects: [Sound](https://papers.cool/arxiv/cs.SD) , [Artificial Intelligence](https://papers.cool/arxiv/cs.AI) , [Computer Vision and Pattern Recognition](https://papers.cool/arxiv/cs.CV) , [Machine Learning](https://papers.cool/arxiv/cs.LG) , [Audio and Speech Processing](https://papers.cool/arxiv/eess.AS) Publish: 2025-09-09 13:54:41 UTC ***
Shard	61 (laksa)
Root Hash	17309916099783778261
Unparsed URL	cool,papers!/arxiv/2509.07756 s443