Papers › Finstreder: Simple and fast Spoken Language Understanding with Finite State...

Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models

29 Jun 2022arXiv:2206.14589archive 2025-07-28

Daniel Bermuth, Alexander Poeppel, Wolfgang Reif

In Spoken Language Understanding (SLU) the task is to extract important information from audio commands, like the intent of what a user wants the system to do and special entities like locations or numbers. This paper presents a simple method for embedding intents and entities into Finite State Transducers, and, in combination with a pretrained general-purpose Speech-to-Text model, allows building SLU-models without any additional training. Building those models is very fast and only takes a few seconds. It is also completely language independent. With a comparison on different benchmarks it is shown that this method can outperform multiple other, more resource demanding SLU approaches.

PaperPDFCode

Code

gitlab.com/Jaco-Assistant/finstreder officialmentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Intent ClassificationSlot FillingSpeech-to-TextSpoken Language Understanding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Intent Classification SLURP Finstreder (Conformer) Accuracy (%) 53.11 #4 of 5 Archive leaderboard report
Intent Classification SLURP Finstreder (Quartznet) Accuracy (%) 43.15 #5 of 5 Archive leaderboard report
Slot Filling SLURP Finstreder (Conformer) F1 0.395 #4 of 5 Archive leaderboard report
Slot Filling SLURP Finstreder (Quartznet) F1 0.313 #5 of 5 Archive leaderboard report
Spoken Language Understanding Fluent Speech Commands Finstreder (Conformer + AMT, character-based) Accuracy (%) 99.8 #1 of 17 Archive leaderboard report
Spoken Language Understanding Fluent Speech Commands Finstreder (Quartznet + AMT) Accuracy (%) 99.7 #3 of 17 Archive leaderboard report
Spoken Language Understanding Fluent Speech Commands Finstreder (Conformer) Accuracy (%) 99.5 #8 of 17 Archive leaderboard report
Spoken Language Understanding Fluent Speech Commands Finstreder (Quartznet) Accuracy (%) 99.2 #12 of 17 Archive leaderboard report
Spoken Language Understanding Fluent Speech Commands Amazon Alexa Accuracy (%) 98.7 #16 of 17 Archive leaderboard report
Spoken Language Understanding Snips-SmartLights Finstreder (Conformer, character-based) Accuracy (%) 89.0 #1 of 7 Archive leaderboard report
Spoken Language Understanding Snips-SmartLights Finstreder (Conformer) Accuracy (%) 88.0 #2 of 7 Archive leaderboard report
Spoken Language Understanding Snips-SmartLights Finstreder (Quartznet) Accuracy (%) 84.8 #4 of 7 Archive leaderboard report
Spoken Language Understanding Snips-SmartSpeaker Finstreder (Conformer, character-based) Accuracy-EN (%) 87.9 #1 of 5 Archive leaderboard report
Spoken Language Understanding Snips-SmartSpeaker Finstreder (Conformer, character-based) Accuracy-FR (%) 86.5 #1 of 5 Archive leaderboard report
Spoken Language Understanding Snips-SmartSpeaker Finstreder (Conformer) Accuracy-EN (%) 80.4 #2 of 5 Archive leaderboard report
Spoken Language Understanding Snips-SmartSpeaker Finstreder (Conformer) Accuracy-FR (%) 78.3 #2 of 5 Archive leaderboard report
Spoken Language Understanding Snips-SmartSpeaker Finstreder (Quartznet) Accuracy-EN (%) 77.6 #3 of 5 Archive leaderboard report
Spoken Language Understanding Snips-SmartSpeaker Finstreder (Quartznet) Accuracy-FR (%) 77.8 #3 of 5 Archive leaderboard report
Spoken Language Understanding Timers and Such Finstreder (Conformer) Accuracy (%) 95.4 #1 of 3 Archive leaderboard report
Spoken Language Understanding Timers and Such Finstreder (Quartznet) Accuracy (%) 90.0 #2 of 3 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