English
Related papers

Related papers: Knowledge-Aware Audio-Grounded Generative Slot Fil…

200 papers

Automated annotation of pedagogical dialogue is a high-stakes task where LLMs often fail without sufficient domain grounding. We present a domain-adapted RAG pipeline for tutoring move annotation. Rather than fine-tuning the generative…

Computation and Language · Computer Science 2026-04-06 Jinsook Lee , Kirk Vanacore , Zhuqian Zhou , Bakhtawar Ahtisham , Rene F. Kizilcec

Real-time speech-to-speech (S2S) models excel at generating natural, low-latency conversational responses but often lack deep knowledge and semantic understanding. Conversely, cascaded systems combining automatic speech recognition, a…

Computation and Language · Computer Science 2026-05-26 So Kuroki , Yotaro Kubo , Takuya Akiba , Yujin Tang

Designing a speech-to-intent (S2I) agent which maps the users' spoken commands to the agents' desired task actions can be challenging due to the diverse grammatical and lexical preference of different users. As a remedy, we discuss a…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-01 Pu Wang , Hugo Van hamme

Knowledge graphs (KGs) enhance the performance of large language models (LLMs) and search engines by providing structured, interconnected data that improves reasoning and context-awareness. However, KGs only focus on text data, thereby…

Computation and Language · Computer Science 2024-08-09 Khai Le-Duc , Quy-Anh Dang , Tan-Hanh Pham , Truong-Son Hy

To segment a signal into blocks to be analyzed, few-shot keyword spotting (KWS) systems often utilize a sliding window of fixed size. Because of the varying lengths of different keywords or their spoken instances, choosing the right window…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-15 Kevin Wilkinghoff , Alessia Cornaggia-Urrigshardt

In recent years, 3D models have been utilized in many applications, such as auto-driver, 3D reconstruction, VR, and AR. However, the scarcity of 3D model data does not meet its practical demands. Thus, generating high-quality 3D models…

Computer Vision and Pattern Recognition · Computer Science 2023-05-26 Weizhi Nie , Ruidong Chen , Weijie Wang , Bruno Lepri , Nicu Sebe

Scaling semantic parsing models for task-oriented dialog systems to new languages is often expensive and time-consuming due to the lack of available datasets. Available datasets suffer from several shortcomings: a) they contain few…

Computation and Language · Computer Science 2021-01-28 Haoran Li , Abhinav Arora , Shuohui Chen , Anchit Gupta , Sonal Gupta , Yashar Mehdad

Modern Text-to-Speech (TTS) systems increasingly leverage Large Language Model (LLM) architectures to achieve scalable, high-fidelity, zero-shot generation. However, these systems typically rely on fixed-frame-rate acoustic tokenization,…

Task oriented language understanding in dialog systems is often modeled using intents (task of a query) and slots (parameters for that task). Intent detection and slot tagging are, in turn, modeled using sentence classification and word…

Computation and Language · Computer Science 2019-11-14 Arash Einolghozati , Sonal Gupta , Mrinal Mohit , Rushin Shah

Dialog state tracking (DST) is a core component in task-oriented dialog systems. Existing approaches for DST mainly fall into one of two categories, namely, ontology-based and ontology-free methods. An ontology-based method selects a value…

Computation and Language · Computer Science 2020-10-29 Jian-Guo Zhang , Kazuma Hashimoto , Chien-Sheng Wu , Yao Wan , Philip S. Yu , Richard Socher , Caiming Xiong

Zero-shot cross-domain dialogue state tracking (DST) enables us to handle task-oriented dialogue in unseen domains without the expense of collecting in-domain data. In this paper, we propose a slot description enhanced generative approach…

Computation and Language · Computer Science 2021-05-11 Zhaojiang Lin , Bing Liu , Seungwhan Moon , Paul Crook , Zhenpeng Zhou , Zhiguang Wang , Zhou Yu , Andrea Madotto , Eunjoon Cho , Rajen Subba

An indispensable component in task-oriented dialogue systems is the dialogue state tracker, which keeps track of users' intentions in the course of conversation. The typical approach towards this goal is to fill in multiple pre-defined…

Computation and Language · Computer Science 2021-01-26 Fanghua Ye , Jarana Manotumruksa , Qiang Zhang , Shenghui Li , Emine Yilmaz

Responding with knowledge has been recognized as an important capability for an intelligent conversational agent. Yet knowledge-grounded dialogues, as training data for learning such a response generation model, are difficult to obtain.…

Computation and Language · Computer Science 2020-02-25 Xueliang Zhao , Wei Wu , Chongyang Tao , Can Xu , Dongyan Zhao , Rui Yan

Direct acoustics-to-word (A2W) systems for end-to-end automatic speech recognition are simpler to train, and more efficient to decode with, than sub-word systems. However, A2W systems can have difficulties at training time when data is…

Computation and Language · Computer Science 2019-04-01 Shane Settle , Kartik Audhkhasi , Karen Livescu , Michael Picheny

It is expensive and difficult to obtain the large number of sentence-level intent and token-level slot label annotations required to train neural network (NN)-based Natural Language Understanding (NLU) components of task-oriented dialog…

Computation and Language · Computer Science 2022-12-16 Rashmi Gangadharaiah , Balakrishnan Narayanaswamy

In this paper, we present a system to showcase the capabilities of the latest state-of-the-art retrieval augmented generation models trained on knowledge-intensive language tasks, such as slot filling, open domain question answering,…

Computation and Language · Computer Science 2022-09-23 Md Faisal Mahbub Chowdhury , Michael Glass , Gaetano Rossiello , Alfio Gliozzo , Nandana Mihindukulasooriya

There is an increasing demand for task-oriented dialogue systems which can assist users in various activities such as booking tickets and restaurant reservations. In order to complete dialogues effectively, dialogue policy plays a key role…

Computation and Language · Computer Science 2019-09-23 Tian Lan , Xianling Mao , Heyan Huang

Recent efforts in Dialogue State Tracking (DST) for task-oriented dialogues have progressed toward open-vocabulary or generation-based approaches where the models can generate slot value candidates from the dialogue history itself. These…

Computation and Language · Computer Science 2020-02-25 Hung Le , Richard Socher , Steven C. H. Hoi

Few-shot Learning (FSL) is aimed to make predictions based on a limited number of samples. Structured data such as knowledge graphs and ontology libraries has been leveraged to benefit the few-shot setting in various tasks. However, the…

Computation and Language · Computer Science 2023-01-27 Hongbin Ye , Ningyu Zhang , Shumin Deng , Xiang Chen , Hui Chen , Feiyu Xiong , Xi Chen , Huajun Chen

In embedding-matching acoustic-to-word (A2W) ASR, every word in the vocabulary is represented by a fixed-dimension embedding vector that can be added or removed independently of the rest of the system. The approach is potentially an elegant…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-21 Hao Yen , Woojay Jeon