pith. sign in

arxiv: 2104.02014 · v2 · pith:55TY6UNYnew · submitted 2021-04-05 · 💻 cs.CL · eess.AS

SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition

Patrick K. O'Neill , Vitaly Lavrukhin , Somshubra Majumdar , Vahid Noroozi , Yuekai Zhang , Oleksii Kuchaiev , Jagadeesh Balam , Yuliya Dovzhenko
show 5 more authors
Keenan Freyberg Michael D. Shulman Boris Ginsburg Shinji Watanabe Georg Kucsko
This is my paper
classification 💻 cs.CL eess.AS
keywords modelsacousticcorpusdatasetsend-to-endformattedfullyhours
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models

    cs.SD 2025-07 unverdicted novelty 7.0

    Audio Flamingo 3 introduces an open large audio-language model achieving new state-of-the-art results on over 20 audio understanding and reasoning benchmarks using a unified encoder and curriculum training on open data.

  2. TRADE: Transducer-Augmented Decoder for Speech LLM

    cs.CL 2026-06 unverdicted novelty 6.0

    TRADE augments multimodal Speech LLMs with a transducer branch for streaming ASR, reporting 6.71% WER offline and 8.40% streaming on the Open ASR Leaderboard from one checkpoint.

  3. Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs

    eess.AS 2026-04 unverdicted novelty 6.0

    A multi-stage training method for LLM-based ASR uses new entropy allocation metrics to achieve competitive benchmark performance with 2.3B parameters while mitigating hallucinations via better encoder-LLM decoupling.

  4. Raon-OpenTTS: Open Models and Data for Robust Text-to-Speech

    eess.AS 2026-05 unverdicted novelty 5.0

    Raon-OpenTTS provides an open 510K-hour curated speech dataset and DiT-based TTS models up to 1B parameters that achieve competitive WER and speaker similarity on benchmarks versus closed models trained on millions of hours.

  5. When Misinformation Speaks and Converses: Rethinking Fact-Checking in Audio Platforms

    cs.CL 2026-04 unverdicted novelty 4.0

    Audio misinformation requires rethinking fact-checking pipelines due to its spoken and conversational properties that traditional text-based methods overlook.