Challenge: Spoken Language Understanding systems parse spoken utterances into semantic structures like dialog acts and slots.
Approach: They propose to use concatenated N-best ASR alternatives to represent utterances . they propose to employ a simpler utteration representation with no special delimiter .
Outcome: The proposed model outperforms the prior state-of-the-art model on DSTC2 dataset.

Similar Papers

MoE-SLU: Towards ASR-Robust Spoken Language Understanding via Mixture-of-Experts (2024.findings-acl)

Copied to clipboard

Challenge: Spoken language understanding (SLU) is a crucial task in task-oriented dialogue systems.
Approach: They propose an ASR-Robust SLU framework based on the mixture-of-experts technique to generate additional transcripts from clean transcripts and use it to weigh the representations of the generated transcripts, ASR transcripts .
Outcome: The proposed framework achieves state-of-the-art on three benchmark SLU datasets.
Speechformer: Reducing Information Loss in Direct Speech Translation (2021.emnlp-main)

Copied to clipboard

Challenge: Current approaches to speech-to-text translation (ST) use a pipeline of two sub-components - an automatic speech recognition (ASR) and a machine translation (MT) model.
Approach: They propose an architecture that avoids initial lossy compression and aggregates information only at a higher level according to more informed linguistic criteria.
Outcome: The proposed architecture achieves gains of up to 0.8 BLEU on the standard MuST-C corpus and up to 4.0 BLUE in a low resource scenario.
Simulating ASR errors for training SLU systems (L18-1)

Copied to clipboard

Challenge: Existing methods to simulate automatic speech recognition errors from manual transcriptions are not available during training of the SLU model.
Approach: They propose to use acoustic and linguistic word embeddings to define a similarity measure between words to predict ASR confusions.
Outcome: The proposed method significantly improves the performance of spoken language understanding systems.
Multi-task Learning of Spoken Language Understanding by Integrating N-Best Hypotheses with Hierarchical Attention (2020.coling-industry)

Copied to clipboard

Challenge: Existing methods to integrate hypotheses into speech recognition systems are noisy and can cause information loss.
Approach: They propose to integrate hypotheses into multi-task learning and transfer learning to improve performance.
Outcome: The proposed model improves domain and intent classification by 19% and 37% compared to current methods . the proposed model could recover transcription and rewrite the query for a better understanding .
Federated Learning for Spoken Language Understanding (2020.coling-main)

Copied to clipboard

Challenge: Existing methods to improve robustness of models focus on a single dataset . but, there are few studies on how to combine merits of different datasets .
Approach: They propose a federated learning framework that could unify datasets and tasks . they propose MV-Encoder as backbone of the framework to provide multi-granularity text representations .
Outcome: The proposed framework improves on two SLU benchmark datasets and federated learning settings.
PRoDeliberation: Parallel Robust Deliberation for End-to-End Spoken Language Understanding (2024.findings-emnlp)

Copied to clipboard

Challenge: End-to-end models for Spoken Language Understanding have been autoregressive, resulting in higher latencies.
Approach: They propose a method that uses Connectionist Temporal Classification to train robust non-autoregressive deliberation models.
Outcome: The proposed method achieves 10x latency reduction over autoregressive models while preserving ability to correct ASR mistranscriptions.
The importance of fillers for text representations of speech transcripts (2020.emnlp-main)

Copied to clipboard

Challenge: Fillers are a type of disfluency that can be a sound ("um" or "uh") filling a pause in an utterance or conversation.
Approach: They propose to represent fillers with deep contextualised embeddings to improve modelling of spoken language and two downstream tasks .
Outcome: The proposed representations improve modelling of spoken language and two downstream tasks, predicting a speaker’s stance and expressed confidence.
Do Slides Help? Multi-modal Context for Automatic Transcription of Conference Talks (2025.emnlp-main)

Copied to clipboard

Challenge: Current automatic speech recognition systems rely on only audio information, ignoring multi-modal context.
Approach: They propose to integrate visual context into existing automatic speech recognition systems to integrate presentation slides with multi-modal information.
Outcome: The proposed model reduces word error rate by approximately 34% across all words and 35% for domain-specific terms compared to baseline model.
Lattice Transformer for Speech Translation (P19-1)

Copied to clipboard

Challenge: Recent advances in sequence modeling have highlighted the strengths of the transformer architecture.
Approach: They propose a general lattice transformer for speech translation where the input is the output of the automatic speech recognition (ASR) they propose 'controllable' lattica attention mechanism to consume latent representations.
Outcome: The proposed model outperforms baseline and lattice LSTM on the Chinese-English translation task.
SLABERT Talk Pretty One Day: Modeling Second Language Acquisition with BERT (2023.acl-long)

Copied to clipboard

Challenge: NLP literature has not given enough attention to the phenomenon of negative transfer . positive transfer refers to the facilitating effects of one language in acquiring another and negative transfer refer to the negative effects between the learner's native [L1] and target [L2] languages.
Approach: They build a Mutlilingual Age Ordered CHILDES dataset to understand the degree to which native Child-Directed Speech (CDS) can help or conflict with English language acquisition.
Outcome: The proposed model enables us to understand the degree to which native Child-Directed Speech (CDS) can help or conflict with English language acquisition.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations