From b5e556a19dc1850dfca56fb992ff1e44e6ad639a Mon Sep 17 00:00:00 2001 From: SuperKogito Date: Wed, 8 Mar 2023 22:12:29 +0100 Subject: [PATCH] add SynAct dataset --- README.md | 1 + src/ser-datasets.csv | 1 + src/ser-datasets.json | 16 +++++++++++++++- 3 files changed, 17 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 5bd3f97..6e65c4a 100644 --- a/README.md +++ b/README.md @@ -4,6 +4,7 @@ The table can be browsed, sorted and searched under https://superkogito.github.i | Dataset | Year | Content | Emotions | Format | Size | Language | Paper | Access | License | |:--------------------------------------------------------------------------------------------------------------------------------------------------|:----------------|:------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------|:------------------------|:------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------|:------------------------------------------------------------------------------------------------------------------------------------------| | [MESD](https://data.mendeley.com/datasets/cy34mh68j9/5) | 2022 | 864 audio files of single-word emotional utterances with Mexican cultural shaping. | 6 emotions provides single-word utterances for anger, disgust, fear, happiness, neutral, and sadness. | Audio | 0,097 GB | Spanish (Mexican) | [The Mexican Emotional Speech Database (MESD): elaboration and assessment based on machine learning](https://pubmed.ncbi.nlm.nih.gov/34891601/) | Open | [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) | +| [SyntAct](https://zenodo.org/record/6573016#.ZAjy_9LMJpj) | 2022 | SyntAct | a synthesized database of three basic emotions and neutral expression based on rule-based manipulation for a diphone synthesizer which we release to the public | Audio | 941 MB | German | [SyntAct: A Synthesized Database of Basic Emotions](http://felix.syntheticspeech.de/publications/synthetic_database.pdf) | Open | [CC BY-SA 4.0](https://creativecommons.org/licenses/by/4.0) | | [MLEnd](https://www.kaggle.com/datasets/jesusrequena/mlend-spoken-numerals) | 2021 | ~32700 audio recordings files produced by 154 speakers. Each audio recording corresponds to one English numeral (from "zero" to "billion") | Intonations: neutral, bored, excited and question | Audio | 2.27 GB | -- | -- | Open | Unknown | | [ASVP-ESD](https://www.kaggle.com/datasets/dejolilandry/asvpesdspeech-nonspeech-emotional-utterances) | 2021 | ~13285 audio files collected from movies, tv shows and youtube containing speech and non-speech. | 12 different natural emotions (boredom, neutral, happiness, sadness, anger, fear, surprise, disgust, excitement, pleasure, pain, disappointment) with 2 levels of intensity. | Audio | 2 GB | Chinese, English, French, Russian and others | -- | Open | Unknown | | [ESD](https://hltsingapore.github.io/ESD/) | 2021 | 29 hours, 3500 sentences, by 10 native English speakers and 10 native Chinese speakers. | 5 emotions: angry, happy, neutral, sad, and surprise. | Audio, Text | 2.4 GB (zip) | Chinese, English | [Seen And Unseen Emotional Style Transfer For Voice Conversion With A New Emotional Speech Dataset](https://arxiv.org/pdf/2010.14794.pdf) | Open | Academic License | diff --git a/src/ser-datasets.csv b/src/ser-datasets.csv index fd7c32f..e2d466e 100644 --- a/src/ser-datasets.csv +++ b/src/ser-datasets.csv @@ -1,5 +1,6 @@ Dataset,Year,Content,Emotions,Format,Size,Language,Paper,Access,License `MESD `_,2022,864 audio files of single-word emotional utterances with Mexican cultural shaping.,"6 emotions provides single-word utterances for anger, disgust, fear, happiness, neutral, and sadness.",Audio,"0,097 GB",Spanish (Mexican),`The Mexican Emotional Speech Database (MESD): elaboration and assessment based on machine learning `_,Open,`CC BY 4.0 `_ +`SyntAct `_,2022,SyntAct, a synthesized database of three basic emotions and neutral expression based on rule-based manipulation for a diphone synthesizer which we release to the public,Audio,941 MB,German,`SyntAct: A Synthesized Database of Basic Emotions `_,Open,`CC BY-SA 4.0 `_ `MLEnd `_,2021,"~32700 audio recordings files produced by 154 speakers. Each audio recording corresponds to one English numeral (from ""zero"" to ""billion"")","Intonations: neutral, bored, excited and question",Audio,2.27 GB,--,--,Open,Unknown `ASVP-ESD `_,2021,"~13285 audio files collected from movies, tv shows and youtube containing speech and non-speech.","12 different natural emotions (boredom, neutral, happiness, sadness, anger, fear, surprise, disgust, excitement, pleasure, pain, disappointment) with 2 levels of intensity.",Audio,2 GB,"Chinese, English, French, Russian and others",--,Open,Unknown `ESD `_,2021,"29 hours, 3500 sentences, by 10 native English speakers and 10 native Chinese speakers.","5 emotions: angry, happy, neutral, sad, and surprise.","Audio, Text",2.4 GB (zip),"Chinese, English",`Seen And Unseen Emotional Style Transfer For Voice Conversion With A New Emotional Speech Dataset `_,Open,Academic License diff --git a/src/ser-datasets.json b/src/ser-datasets.json index 00f9f0d..b7fe9b4 100644 --- a/src/ser-datasets.json +++ b/src/ser-datasets.json @@ -13,6 +13,20 @@ "Paper-link": "https://pubmed.ncbi.nlm.nih.gov/34891601/", "License-link": "https://creativecommons.org/licenses/by/4.0/" }, + "SyntAct": { + "Year": 2022, + "Content": "SyntAct", + "Emotions": " a synthesized database of three basic emotions and neutral expression based on rule-based manipulation for a diphone synthesizer which we release to the public", + "Format": "Audio", + "Size": "941 MB", + "Language": "German", + "Paper": "SyntAct: A Synthesized Database of Basic Emotions", + "Access": "Open", + "License": "CC BY-SA 4.0", + "Dataset-link": "https://zenodo.org/record/6573016#.ZAjy_9LMJpj", + "Paper-link": "http://felix.syntheticspeech.de/publications/synthetic_database.pdf", + "License-link": "https://creativecommons.org/licenses/by/4.0" + }, "MLEnd": { "Year": 2021, "Content": "~32700 audio recordings files produced by 154 speakers. Each audio recording corresponds to one English numeral (from \"zero\" to \"billion\")", @@ -587,4 +601,4 @@ "Paper-link": "http://kom.aau.dk/~tb/speech/Emotions/des.pdf", "License-link": "--" } -} \ No newline at end of file +}