SOTAVerified

Spoken Language Understanding

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 201–250 of 550 papers

TitleStatusHype
Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU—0
Exploring the Effect of Segmentation and Vocabulary Size on Speech Tokenization for Speech Language Models—0
BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model—0
Engineering Statistical Dialog State Trackers: A Case Study on DSTC—0
Exploring Transfer Learning For End-to-End Spoken Language Understanding—0
Extrinsic Evaluation of Dialog State Tracking and Predictive Metrics for Dialog Policy Optimization—0
Benchmarking Transformers-based models on French Spoken Language Understanding tasks—0
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition—0
An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking—0
Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning—0
End-to-End Spoken Language Understanding for Generalized Voice Assistants—0
Few-Shot Spoken Language Understanding via Joint Speech-Text Models—0
Fillers in Spoken Language Understanding: Computational and Psycholinguistic Perspectives—0
Finding Task-specific Subnetworks in Multi-task Spoken Language Understanding Model—0
End-to-end spoken language understanding using joint CTC loss and self-supervised, pretrained acoustic encoders—0
End-to-End Spoken Language Understanding: Performance analyses of a voice command task in a low resource setting—0
Avaya Conversational Intelligence: A Real-Time System for Spoken Language Understanding in Human-Human Call Center Conversations—0
An Empirical Study of Automatic Chinese Word Segmentation for Spoken Language Understanding and Named Entity Recognition—0
From Audio to Semantics: Approaches to end-to-end spoken language understanding—0
On joint training with interfaces for spoken language understanding—0
End-to-end spoken language understanding using transformer networks and self-supervised pre-trained features—0
Automatic Token and Turn Level Language Identification for Code-Switched Text Dialog: An Analysis Across Language Pairs and Corpora—0
Generative Context-aware Fine-tuning of Self-supervised Speech Models—0
End-to-End Spoken Language Understanding Without Full Transcripts—0
End-to-End Spoken Language Translation—0
Global-Locally Self-Attentive Encoder for Dialogue State Tracking—0
Graph-based alignment of narratives for automated neurological assessment—0
Automatic Data Expansion for Customer-care Spoken Language Understanding—0
Graph Databases for Designing High-Performance Speech Recognition Grammars—0
Hallucination of speech recognition errors with sequence to sequence learning—0
HAN: Higher-order Attention Network for Spoken Language Understanding—0
HC^2L: Hybrid and Cooperative Contrastive Learning for Cross-lingual Spoken Language Understanding—0
An Efficient Approach to Encoding Context for Spoken Language Understanding—0
A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding—0
Adapting a FrameNet Semantic Parser for Spoken Language Understanding Using Adversarial Learning—0
HRItk: The Human-Robot Interaction ToolKit Rapid Development of Speech-Centric Interactive Systems in ROS—0
Human Evaluation of Conceptual Route Graphs for Interpreting Spoken Route Descriptions—0
Human-Machine Dialogue as a Stochastic Game—0
End-to-end Spoken Conversational Question Answering: Task, Dataset and Model—0
Hybrid Dialog State Tracker with ASR Features—0
End-to-end speech-to-dialog-act recognition—0
Hyper-parameter Optimisation of Gaussian Process Reinforcement Learning for Statistical Dialogue Management—0
I^2KD-SLU: An Intra-Inter Knowledge Distillation Framework for Zero-Shot Cross-Lingual Spoken Language Understanding—0
IBM's Belief Tracker: Results On Dialog State Tracking Challenge Datasets—0
Identifying Domain Independent Update Intents in Task Based Dialogs—0
Impact Analysis of the Use of Speech and Language Models Pretrained by Self-Supersivion for Spoken Language Understanding—0
Automated Speech Recognition Technology for Dialogue Interaction with Non-Native Interlocutors—0
Improving End-to-End Speech Processing by Efficient Text Data Utilization with Latent Synthesis—0
End-to-End Neural Transformer Based Spoken Language Understanding—0
End-to-end model for named entity recognition from speech without paired training data—0
Show:102550
← PrevPage 5 of 11Next →
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