SOTAVerified

Spoken Language Understanding

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 521–530 of 550 papers

TitleStatusHype
Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic FeaturesCode0
Augmenting Slot Values and Contexts for Spoken Language Understanding with Pretrained ModelsCode0
EDA: Enriching Emotional Dialogue Acts using an Ensemble of Neural AnnotatorsCode0
Uni-MIS: United Multiple Intent Spoken Language Understanding via Multi-View Intent-Slot InteractionCode0
Discourse-Wizard: Discovering Deep Discourse Structure in your Conversation with RNNsCode0
Slot-Gated Modeling for Joint Slot Filling and Intent PredictionCode0
Text Matters but Speech Influences: A Computational Analysis of Syntactic Ambiguity ResolutionCode0
Pro-HAN: A Heterogeneous Graph Attention Network for Profile-Based Spoken Language UnderstandingCode0
Audio-Linguistic Embeddings for Spoken SentencesCode0
ISO-Standard Domain-Independent Dialogue Act Tagging for Conversational AgentsCode0
Show:102550
← PrevPage 53 of 55Next →
All datasetsFluent Speech CommandsSnips-SmartLightsSnips-SmartSpeakerSpoken-SQuADTimers and Such

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Finstreder (Conformer + AMT, character-based)Accuracy (%)99.8—Unverified
2UniverSLUAccuracy (%)99.8—Unverified
3E2E SLP two-stepAccuracy (%)99.7—Unverified
4textual-kd-sluAccuracy (%)99.7—Unverified
5Wav2Vec2.0-ClassifierAccuracy (%)99.7—Unverified
6Finstreder (Quartznet + AMT)Accuracy (%)99.7—Unverified
7Wav2vec 2.0 SSLAccuracy (%)99.6—Unverified
8Finstreder (Conformer)Accuracy (%)99.5—Unverified
9AT-ATAccuracy (%)99.5—Unverified
10BERT, AC PretrainingAccuracy (%)99.4—Unverified
#ModelMetricClaimedVerifiedStatus
1Finstreder (Conformer, character-based)Accuracy (%)89—Unverified
2Finstreder (Conformer)Accuracy (%)88—Unverified
3AT-ATAccuracy (%)84.9—Unverified
4Finstreder (Quartznet)Accuracy (%)84.8—Unverified
5SnipsAccuracy (%)84.2—Unverified
6GoogleAccuracy (%)79.3—Unverified
7Real + syntheticAccuracy (%)71.4—Unverified
#ModelMetricClaimedVerifiedStatus
1Finstreder (Conformer, character-based)Accuracy-EN (%)87.9—Unverified
2Finstreder (Conformer)Accuracy-EN (%)80.4—Unverified
3Finstreder (Quartznet)Accuracy-EN (%)77.6—Unverified
4SnipsAccuracy-EN (%)68.7—Unverified
5GoogleAccuracy-EN (%)47.8—Unverified
#ModelMetricClaimedVerifiedStatus
1ALBERTF1 score77.1—Unverified
2SpeechBERTF1 score71.75—Unverified
3QANet + GANF1 score63.11—Unverified
4BaselineF1 score58.71—Unverified
#ModelMetricClaimedVerifiedStatus
1Finstreder (Conformer)Accuracy (%)95.4—Unverified
2Finstreder (Quartznet)Accuracy (%)90—Unverified
3BaselineAccuracy (%)81.6—Unverified