Datasets › Fluent Speech Commands

Fluent Speech Commands

Introduced by Loren Lugosch et al. in Speech Model Pre-training for End-to-End Spoken Language Understanding7 Apr 2019 archive 2025-07-28

Fluent Speech Commands is an open source audio dataset for spoken language understanding (SLU) experiments. Each utterance is labeled with "action", "object", and "location" values; for example, "turn the lights on in the kitchen" has the label {"action": "activate", "object": "lights", "location": "kitchen"}. A model must predict each of these values, and a prediction for an utterance is deemed to be correct only if all values are correct.

The task is very simple, but the dataset is large and flexible to allow for many types of experiments: for instance, one can vary the number of speakers, or remove all instances of a particular sentence and test whether a model trained on the remaining sentences can generalize.

Homepage Benchmarks Papers JSON

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

		First row (archive order)	Paper	Code
Spoken Language Understanding	Fluent Speech Commands	Finstreder (Conformer + AMT, character-based) Accuracy (%) 99.8	Finstreder: Simple and fast Spoken Language...	gitlab.com/Jaco-Assistant/Jaco-Master +1	17	Compare

Papers archive 2025-07-28

13 shown of 13 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 57. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

			Date	Samples run Syntology
UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions	0	1	4 Oct 2023	not harvested
SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks	0	1	1 Mar 2023	not harvested
Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models	2	5	29 Jun 2022	not harvested
Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?	0	1	29 Nov 2021	not harvested
FANS: Fusing ASR and NLU for on-device SLU	0	1	31 Oct 2021	not harvested
End-to-End Spoken Language Understanding for Generalized Voice Assistants	0	1	16 Jun 2021	not harvested
Sequential End-to-End Intent and Slot Label Classification and Localization	0	1	8 Jun 2021	not harvested
Integration of Pre-trained Networks with Continuous Token Interface for End-to-End Spoken Language Understanding	0	1	15 Apr 2021	not harvested
Speech-language Pre-training for End-to-end Spoken Language Understanding	0	1	11 Feb 2021	not harvested
Exploring Transfer Learning For End-to-End Spoken Language Understanding	0	1	15 Dec 2020	not harvested
Two-stage Textual Knowledge Distillation for End-to-End Spoken Language Understanding	1	1	25 Oct 2020	not harvested
Improving End-to-End Speech-to-Intent Classification with Reptile	0	1	5 Aug 2020	not harvested
Speech Model Pre-training for End-to-End Spoken Language Understanding	2	1	7 Apr 2019	not harvested

Dataset loaders archive 2025-07-28

rayyanahmed26042005/git-G160tf

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Spoken Language Understanding Voice Query Recognition

License archive 2025-07-28

Custom (research-only)

Modalities archive 2025-07-28

Audio

Languages archive 2025-07-28

English

Variants archive 2025-07-28

Fluent Speech Commands

1 variant name, as the archive lists them.

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