1. SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition
- Author
-
O'Neill, Patrick K., Lavrukhin, Vitaly, Majumdar, Somshubra, Noroozi, Vahid, Zhang, Yuekai, Kuchaiev, Oleksii, Balam, Jagadeesh, Dovzhenko, Yuliya, Freyberg, Keenan, Shulman, Michael D., Ginsburg, Boris, Watanabe, Shinji, and Kucsko, Georg
- Subjects
Computer Science - Computation and Language ,Electrical Engineering and Systems Science - Audio and Speech Processing - Abstract
In the English speech-to-text (STT) machine learning task, acoustic models are conventionally trained on uncased Latin characters, and any necessary orthography (such as capitalization, punctuation, and denormalization of non-standard words) is imputed by separate post-processing models. This adds complexity and limits performance, as many formatting tasks benefit from semantic information present in the acoustic signal but absent in transcription. Here we propose a new STT task: end-to-end neural transcription with fully formatted text for target labels. We present baseline Conformer-based models trained on a corpus of 5,000 hours of professionally transcribed earnings calls, achieving a CER of 1.7. As a contribution to the STT research community, we release the corpus free for non-commercial use at https://datasets.kensho.com/datasets/scribe., Comment: 5 pages, 1 figure. Submitted to INTERSPEECH 2021
- Published
- 2021