Related papers: Learning Fault-tolerant Speech Parsing with SCREEN
Spoken language understanding (SLU) requires a model to analyze input acoustic signal to understand its linguistic content and make predictions. To boost the models' performance, various pre-training methods have been proposed to learn rich…
Foundation models based on large language models (LLMs) have shown great success in handling various tasks and modalities. However, adapting these models for general-purpose audio-language tasks is challenging due to differences in acoustic…
In Natural Language (NL) applications, there is often a mismatch between what the NL interface is capable of interpreting and what a lay user knows how to express. This work describes a novel natural language interface that reduces this…
Our goal is to create an interactive natural language interface that efficiently and reliably learns from users to complete tasks in simulated robotics settings. We introduce a neural semantic parsing system that learns new high-level…
End-to-end architectures have been recently proposed for spoken language understanding (SLU) and semantic parsing. Based on a large amount of data, those models learn jointly acoustic and linguistic-sequential features. Such architectures…
Recently, supervised speech separation has made great progress. However, limited by the nature of supervised training, most existing separation methods require ground-truth sources and are trained on synthetic datasets. This ground-truth…
Semantic parsing is challenging due to the structure gap and the semantic gap between utterances and logical forms. In this paper, we propose an unsupervised semantic parsing method - Synchronous Semantic Decoding (SSD), which can…
Multi-modal generative document parsing systems challenge traditional evaluation: unlike deterministic OCR or layout models, they often produce semantically correct yet structurally divergent outputs. Conventional metrics-CER, WER, IoU, or…
Natural Language Processing enables computers to understand human language by analysing and classifying text efficiently with deep-level grammatical and semantic features. Existing models capture features by learning from large corpora with…
Syllables are compositional units of spoken language that efficiently structure human speech perception and production. However, current neural speech representations lack such structure, resulting in dense token sequences that are costly…
In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…
Computing devices have recently become capable of interacting with their end users via natural language. However, they can only operate within a limited "supported" domain of discourse and fail drastically when faced with an out-of-domain…
Deep learning models have become an increasingly preferred option for biometric recognition systems, such as speaker recognition. SincNet, a deep neural network architecture, gained popularity in speaker recognition tasks due to its…
Free-text promptable 3D medical image segmentation offers an intuitive and clinically flexible interaction paradigm. However, current methods are highly sensitive to linguistic variability: minor changes in phrasing can cause substantial…
We introduce a Recursive INsertion-based Encoder (RINE), a novel approach for semantic parsing in task-oriented dialog. Our model consists of an encoder network that incrementally builds the semantic parse tree by predicting the…
Zero-shot cross-lingual information extraction(IE) aims at constructing an IE model for some low-resource target languages, given annotations exclusively in some rich-resource languages. Recent studies based on language-universal features…
Speech fluency/disfluency can be evaluated by analyzing a range of phonetic and prosodic features. Deep neural networks are commonly trained to map fluency-related features into the human scores. However, the effectiveness of deep…
A recent line of research on spoken language assessment (SLA) employs neural models such as BERT and wav2vec 2.0 (W2V) to evaluate speaking proficiency across linguistic and acoustic modalities. Although both models effectively capture…
Structured embedding transformations offer a promising approach for enhancing the efficiency and coherence of language model inference. The introduction of Structural Embedding Projection (SEP) provides a mechanism for refining token…
We propose a bottom-up framework for automatic speech recognition (ASR) in syllable-based languages by unifying language-universal articulatory attribute modeling with syllable-level prediction. The system first recognizes sequences or…