Skip to content

Latest commit

 

History

19 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 

Repository files navigation

arthur-awesome-speech-recognition

(Work in Progress)

Here is a collection of my own reading in speech recognition and related topics.

Speech Recognizers

Leaderboard to track:

I often track -

wav2vec2-related papers

The five most important ones which everyone should read -

The models

Later development

Language model integration

SFT

Work in Progress.

Whisper

The original paper

Open Whisper-style Speech Model (OWSM)

Other Whisper-style models:

Interesting Variants:

Nemo-related

Phi-related

Common Architectures

Speech Datasets

Some general websites

  • Open SLR Collections of free speech dataset.
  • LDC OG of language resources. Fees for non-members can be hefty.

Individual Datasets grouped by languages

Multilingual

  • Babel (Where is it now?)
  • Voxpopuli Collected from 2009-2020 European Parliament event recordings. >400k hours of data. (Paper)
  • Multilingual LibriSpeech (MLS) A multilingual version of libri-light. It's still heavily tilted towards English, but it also contains significant amount of German, Spanish and 6 other languages. (Paper)
  • Common Voice A multilingual dataset. When you test on CV, remember that there are multiple versions of the dataset. On HuggingFace, also know that some of these databases are gated. (i.e., requires login)
  • FLEURS Standard multilingual dataset for ASR and LID purpose.

English-only

  • Librispeech One of the golden benchmarks in ASR. (Paper)
  • Libri-Light In a sense, it is the extension of Librispeech but with 60k hour of unlabelled data. wav2vec2's models prefixed with -Lv60 are speech representation, for example, are all pre-trained with this dataset. (Paper)
  • LibriSpeech-PC LibriSpeech with punctuation and capitalization (PC) (Paper)
  • Libri-Heavy Labeled version of libri-light also annotated with punctuation and context(Paper) All segments are short (<20s). The group also release a version with long duration called libriheavy-long.

Portuguese

Cantonese

  • CommonVoice and MLS both have subsets on Cantonese
  • MDCC Dataset (The Paper is also a survey on different Cantonese dataset.)

Vietnamese

Other awesome lists:

Speech Database on different stacks.

Hugging Face: (Note: You often need to hack the code to get it working.)

Conferences

  • ISCA Archive If you want to search for all Interspeech conference papers. (Or Eurospeech/ICSLP if you still remember them...)
  • ICASSP Another OG yearly conference on speech. Sad. Not all the papers are archived. So you may need to try your luck to see if the authors put them on archive.

The two are specific to speech. These days peeps love to publish on AAAI and NeurIPS. You know where to find them already.

Journals

Not exactly, but they are super cool

Cool TTS links

Important techniques (unsorted)

Great Explainers

Matrix Calculus If you are never confused about the gradient derivation in our field, you probably haven't looked deep enough into the math...

Reinforcement Learning

Language Datasets

Large Language Model

See LLM.md.

AI-related groups I admin (and browse daily)

About

My own "awesome" collection of speech recognition resources

Resources

Stars

1 star

Watchers

2 watching

Forks

Releases

Packages

Used by

Contributors