English
Related papers

Related papers: A neural prosody encoder for end-ro-end dialogue a…

200 papers

Dialogue act recognition is an important part of natural language understanding. We investigate the way dialogue act corpora are annotated and the learning approaches used so far. We find that the dialogue act is context-sensitive within…

Computation and Language · Computer Science 2018-05-17 Chandrakant Bothe , Cornelius Weber , Sven Magg , Stefan Wermter

In automatic speech recognition (ASR) what a user says depends on the particular context she is in. Typically, this context is represented as a set of word n-grams. In this work, we present a novel, all-neural, end-to-end (E2E) ASR sys- tem…

Audio and Speech Processing · Electrical Eng. & Systems 2018-08-09 Golan Pundak , Tara N. Sainath , Rohit Prabhavalkar , Anjuli Kannan , Ding Zhao

Recently, encoder-decoder neural networks have shown impressive performance on many sequence-related tasks. The architecture commonly uses an attentional mechanism which allows the model to learn alignments between the source and the target…

Computation and Language · Computer Science 2017-11-06 Andros Tjandra , Sakriani Sakti , Satoshi Nakamura

Identifying the features learned by neural networks is a core challenge in mechanistic interpretability. Sparse autoencoders (SAEs), which learn a sparse, overcomplete dictionary that reconstructs a network's internal activations, have been…

Machine Learning · Computer Science 2024-05-27 Dan Braun , Jordan Taylor , Nicholas Goldowsky-Dill , Lee Sharkey

Dialogue Act Recognition (DAR) is a challenging problem in dialogue interpretation, which aims to attach semantic labels to utterances and characterize the speaker's intention. Currently, many existing approaches formulate the DAR problem…

Computation and Language · Computer Science 2017-11-16 Zheqian Chen , Rongqin Yang , Zhou Zhao , Deng Cai , Xiaofei He

The recognition of emotion and dialogue acts enriches conversational analysis and help to build natural dialogue systems. Emotion interpretation makes us understand feelings and dialogue acts reflect the intentions and performative…

Computation and Language · Computer Science 2020-03-17 Chandrakant Bothe , Cornelius Weber , Sven Magg , Stefan Wermter

End-to-end (E2E) approach is gradually replacing hybrid models for automatic speech recognition (ASR) tasks. However, the optimization of E2E models lacks an intuitive method for handling decoding shifts, especially in scenarios with a…

Computation and Language · Computer Science 2024-03-04 Heyang Liu , Yu Wang , Yanfeng Wang

Embodied agents need to be able to interact in natural language understanding task descriptions and asking appropriate follow up questions to obtain necessary information to be effective at successfully accomplishing tasks for a wide range…

Computation and Language · Computer Science 2022-09-28 Spandana Gella , Aishwarya Padmakumar , Patrick Lange , Dilek Hakkani-Tur

Automatic Video Dubbing (AVD) generates speech aligned with lip motion and facial emotion from scripts. Recent research focuses on modeling multimodal context to enhance prosody expressiveness but overlooks two key issues: 1) Multiscale…

Multimedia · Computer Science 2025-01-03 Yuan Zhao , Rui Liu , Gaoxiang Cong

Monaural multi-speaker automatic speech recognition (ASR) remains challenging due to data scarcity and the intrinsic difficulty of recognizing and attributing words to individual speakers, particularly in overlapping speech. Recent advances…

Computation and Language · Computer Science 2026-05-29 Xinlu He , Jacob Whitehill

This paper describes an end-to-end (E2E) neural architecture for the audio rendering of small portions of display content on low resource personal computing devices. It is intended to address the problem of accessibility for vision-impaired…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-13 Liu Chen , Michael Deisher , Munir Georges

Attention-based encoder-decoder neural network models have recently shown promising results in goal-oriented dialogue systems. However, these models struggle to reason over and incorporate state-full knowledge while preserving their…

Computation and Language · Computer Science 2020-01-29 Firas Kassawat , Debanjan Chaudhuri , Jens Lehmann

Unlike traditional cascaded pipelines, end-to-end (E2E) spoken dialogue systems preserve full differentiability and capture non-phonemic information, making them well-suited for modeling spoken interactions. However, existing E2E approaches…

Computation and Language · Computer Science 2025-06-03 Siddhant Arora , Jinchuan Tian , Hayato Futami , Jee-weon Jung , Jiatong Shi , Yosuke Kashiwagi , Emiru Tsunoo , Shinji Watanabe

The ability to model and automatically detect dialogue act is an important step toward understanding spontaneous speech and Instant Messages. However, it has been difficult to infer a dialogue act from a surface utterance because it highly…

Computation and Language · Computer Science 2018-06-05 AbdelRahim Elmadany , Sherif Abdou , Mervat Gheith

Recent advances in the Active Speaker Detection (ASD) problem build upon a two-stage process: feature extraction and spatio-temporal context aggregation. In this paper, we propose an end-to-end ASD workflow where feature learning and…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Juan Leon Alcazar , Moritz Cordes , Chen Zhao , Bernard Ghanem

Attention-based contextual biasing approaches have shown significant improvements in the recognition of generic and/or personal rare-words in End-to-End Automatic Speech Recognition (E2E ASR) systems like neural transducers. These…

Computation and Language · Computer Science 2023-05-10 Xuandi Fu , Kanthashree Mysore Sathyendra , Ankur Gandhe , Jing Liu , Grant P. Strimel , Ross McGowan , Athanasios Mouchtaris

Encoder-decoder based neural architectures serve as the basis of state-of-the-art approaches in end-to-end open domain dialog systems. Since most of such systems are trained with a maximum likelihood~(MLE) objective they suffer from issues…

Language identification (LID) has relevance in many speech processing applications. For the automatic recognition of code-switching speech, the conventional approaches often employ an LID system for detecting the languages present within an…

Computation and Language · Computer Science 2019-07-16 Sreeram Ganji , Kunal Dhawan , Kumar Priyadarshi , Rohit Sinha

While deep learning models have made significant advances in supervised classification problems, the application of these models for out-of-set verification tasks like speaker recognition has been limited to deriving feature embeddings. The…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-12 Shreyas Ramoji , Prashant Krishnan , Sriram Ganapathy

While AI agents demonstrate remarkable capabilities in reasoning and tool use, they remain fundamentally reactive: they compute responses only after explicit user prompts. This paradigm ignores a critical opportunity: the idle time between…

Computation and Language · Computer Science 2026-05-27 Haoyi Hu , Qirong Lyu , Xianghan Kong , Weiwen Liu , Jianghao Lin , Zixuan Guo , Yan Xu , Yasheng Wang , Weinan Zhang , Yong Yu