Papers › SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network
SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network
William Chan, Daniel Park, Chris Lee, Yu Zhang, Quoc Le, Mohammad Norouzi
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Speech Recognition | AMI IMH | SpeechStew (100M) | Word Error Rate (WER) | 9 | #2 of 2 | Archive leaderboard | report |
| Speech Recognition | AMI SDM1 | SpeechStew (100M) | Word Error Rate (WER) | 21.7 | #2 of 2 | Archive leaderboard | report |
| Speech Recognition | CHiME-6 dev_gss12 | SpeechStew (1B) | Word Error Rate (WER) | 31.9 | #3 of 4 | Archive leaderboard | report |
| Speech Recognition | CHiME-6 eval | SpeechStew (1B) | Word Error Rate (WER) | 38.9 | #3 of 3 | Archive leaderboard | report |
| Speech Recognition | Common Voice | SpeechStew (1B) | Test WER | 10.8% | #2 of 2 | Archive leaderboard | report |
| Speech Recognition | LibriSpeech test-clean | SpeechStew (1B) | Word Error Rate (WER) | 1.7 | #9 of 64 | Archive leaderboard | report |
| Speech Recognition | LibriSpeech test-clean | SpeechStew (100M) | Word Error Rate (WER) | 2.0 | #23 of 64 | Archive leaderboard | report |
| Speech Recognition | LibriSpeech test-other | SpeechStew (1B) | Word Error Rate (WER) | 3.3 | #9 of 53 | Archive leaderboard | report |
| Speech Recognition | LibriSpeech test-other | SpeechStew (100M) | Word Error Rate (WER) | 4.0 | #16 of 53 | Archive leaderboard | report |
| Speech Recognition | Switchboard CallHome | SpeechStew (100M) | Word Error Rate (WER) | 8.3 | #1 of 1 | Archive leaderboard | report |
| Speech Recognition | Switchboard SWBD | SpeechStew (100M) | Word Error Rate (WER) | 4.7 | #1 of 1 | Archive leaderboard | report |
| Speech Recognition | Tedlium | SpeechStew (100M) | Word Error Rate (WER) | 5.3 | #4 of 4 | Archive leaderboard | report |
| Speech Recognition | WSJ eval92 | Speechstew 100M | Word Error Rate (WER) | 1.3 | #1 of 17 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections