Pith. sign in

REVIEW 5 cited by

SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2104.02133 v3 pith:4AU7VBUL submitted 2021-04-05 cs.CL cs.LG

William Chan , Daniel Park , Chris Lee , Yu Zhang , Quoc Le , Mohammad Norouzi This is my paper
classification cs.CLcs.LG
keywords speechstewlanguagemodelspeechdatasetsrecognitionwithoutavailable
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present SpeechStew, a speech recognition model that is trained on a combination of various publicly available speech recognition datasets: AMI, Broadcast News, Common Voice, LibriSpeech, Switchboard/Fisher, Tedlium, and Wall Street Journal. SpeechStew simply mixes all of these datasets together, without any special re-weighting or re-balancing of the datasets. SpeechStew achieves SoTA or near SoTA results across a variety of tasks, without the use of an external language model. Our results include 9.0\% WER on AMI-IHM, 4.7\% WER on Switchboard, 8.3\% WER on CallHome, and 1.3\% on WSJ, which significantly outperforms prior work with strong external language models. We also demonstrate that SpeechStew learns powerful transfer learning representations. We fine-tune SpeechStew on a noisy low resource speech dataset, CHiME-6. We achieve 38.9\% WER without a language model, which compares to 38.6\% WER to a strong HMM baseline with a language model.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. OLMoASR: Open Models and Data for Training Robust Speech Recognition Models

    cs.SD 2025-08 conditional novelty 7.0 of 10

    An open 1M-hour English speech dataset plus Whisper-architecture models trained on it match Whisper's word error rates on short and long-form benchmarks.

  2. CAM\~OES: A Comprehensive Automatic Speech Recognition Benchmark for European Portuguese

    cs.CL 2025-08 conditional novelty 6.0 of 10

    CAMOES is a new open benchmark and model collection for European Portuguese ASR, cutting word error rate by about 35% over the best zero-shot model.

  3. OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning

    cs.CL 2025-05 conditional novelty 5.0 of 10

    OWSM v4 models, trained on a cleaned 166k-hour multilingual YODAS subset, beat prior open OWSM models and are competitive with Whisper and MMS on several benchmarks.

  4. Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use

    cs.CL 2025-05 conditional novelty 5.0 of 10

    The Loquacious Set is a curated 25,000-hour English ASR corpus combining six open datasets, with commercial-ready licenses and conformer baselines that reach 4.6% WER on LibriSpeech test-other.

  5. Analyzing and Fine-Tuning Whisper Models for Multilingual Pilot Speech Transcription in the Cockpit

    cs.CL 2025-06 conditional novelty 4.0 of 10

    LoRA fine-tuning plus custom text normalization reduces Whisper word error rate on cockpit pilot speech from 68.49% to 26.26%.

Pith tools