SOTAVerified

Spoken Language Understanding

Papers

Showing 51100 of 550 papers

TitleStatusHype
N-Best ASR Transformer: Enhancing SLU Performance using Multiple ASR HypothesesCode1
LiveLongBench: Tackling Long-Context Understanding for Spoken Texts from Live StreamsCode1
Speak or Chat with Me: End-to-End Spoken Language Understanding System with Flexible InputsCode1
Mitigating the Impact of Speech Recognition Errors on Spoken Question Answering by Adversarial Domain AdaptationCode1
WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language ModelsCode1
Recurrent Neural Networks with Pre-trained Language Model Embedding for Slot Filling TaskCode0
QUADS: QUAntized Distillation Framework for Efficient Speech Language UnderstandingCode0
A dataset for resolving referring expressions in spoken dialogue via contextual query rewrites (CQR)Code0
ReCoMIF: Reading comprehension based multi-source information fusion network for Chinese spoken language understandingCode0
Out-of-distribution generalisation in spoken language understandingCode0
Performance Analysis of Speech Encoders for Low-Resource SLU and ASR in Tunisian DialectCode0
New Semantic Task for the French Spoken Language Understanding MEDIA BenchmarkCode0
A Comparative Study on E-Branchformer vs Conformer in Speech Recognition, Translation, and Understanding TasksCode0
On the Use of External Data for Spoken Named Entity RecognitionCode0
Pro-HAN: A Heterogeneous Graph Attention Network for Profile-Based Spoken Language UnderstandingCode0
Robust Unstructured Knowledge Access in Conversational Dialogue with ASR ErrorsCode0
A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot FillingCode0
Measuring the Effect of Transcription Noise on Downstream Language Understanding TasksCode0
Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and UnderstandingCode0
Speech Understanding on Tiny Devices with A Learning CacheCode0
A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot FillingCode0
Learning ASR-Robust Contextualized Embeddings for Spoken Language UnderstandingCode0
Leveraging Multilingual Self-Supervised Pretrained Models for Sequence-to-Sequence End-to-End Spoken Language UnderstandingCode0
Neural Networks approaches focused on French Spoken Language Understanding: application to the MEDIA Evaluation TaskCode0
SDNet: Contextualized Attention-based Deep Network for Conversational Question AnsweringCode0
Joint Automatic Speech Recognition And Structure Learning For Better Speech UnderstandingCode0
Incorporating Instructional Prompts into a Unified Generative Framework for Joint Multiple Intent Detection and Slot FillingCode0
ISO-Standard Domain-Independent Dialogue Act Tagging for Conversational AgentsCode0
How Time Matters: Learning Time-Decay Attention for Contextual Spoken Language Understanding in DialoguesCode0
HIT-SCIR at MMNLU-22: Consistency Regularization for Multilingual Spoken Language UnderstandingCode0
Improving Slot Filling in Spoken Language Understanding with Joint Pointer and AttentionCode0
"KAN you hear me?" Exploring Kolmogorov-Arnold Networks for Spoken Language UnderstandingCode0
From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language UnderstandingCode0
FlowQA: Grasping Flow in History for Conversational Machine ComprehensionCode0
Fully Statistical Neural Belief TrackingCode0
Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text modelsCode0
MultiMed: Multilingual Medical Speech Recognition via Attention Encoder DecoderCode0
Graph-Based Semi-Supervised Conditional Random Fields For Spoken Language Understanding Using Unaligned DataCode0
Fast Intent Classification for Spoken Language UnderstandingCode0
Back Transcription as a Method for Evaluating Robustness of Natural Language Understanding Models to Speech Recognition ErrorsCode0
Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language UnderstandingCode0
GL-CLeF: A Global-Local Contrastive Learning Framework for Cross-lingual Spoken Language UnderstandingCode0
A Unified Framework for Multi-intent Spoken Language Understanding with promptingCode0
Leveraging Cross-Lingual Transfer Learning in Spoken Named Entity Recognition SystemsCode0
An Investigation of the Combination of Rehearsal and Knowledge Distillation in Continual Learning for Spoken Language UnderstandingCode0
Augmenting Slot Values and Contexts for Spoken Language Understanding with Pretrained ModelsCode0
Audio-Linguistic Embeddings for Spoken SentencesCode0
Exploring the Limits of Natural Language Inference Based Setup for Few-Shot Intent DetectionCode0
GL-CLeF: A Global–Local Contrastive Learning Framework for Cross-lingual Spoken Language UnderstandingCode0
EDA: Enriching Emotional Dialogue Acts using an Ensemble of Neural AnnotatorsCode0
Show:102550
← PrevPage 2 of 11Next →

Benchmark Results

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