中文
相关论文

相关论文: Chain-of-Thought Training for Open E2E Spoken Dial…

200 篇论文

Building robust and general dialogue models for spoken conversations is challenging due to the gap in distributions of spoken and written data. This paper presents our approach to build generalized models for the Knowledge-grounded…

计算与语言 · 计算机科学 2022-03-09 Ruijie Yan , Shuang Peng , Haitao Mi , Liang Jiang , Shihui Yang , Yuchi Zhang , Jiajun Li , Liangrui Peng , Yongliang Wang , Zujie Wen

Dialog history plays an important role in spoken language understanding (SLU) performance in a dialog system. For end-to-end (E2E) SLU, previous work has used dialog history in text form, which makes the model dependent on a cascaded…

计算与语言 · 计算机科学 2022-04-12 Vishal Sunder , Samuel Thomas , Hong-Kwang J. Kuo , Jatin Ganhotra , Brian Kingsbury , Eric Fosler-Lussier

Training an end-to-end (E2E) neural network speech-to-intent (S2I) system that directly extracts intents from speech requires large amounts of intent-labeled speech data, which is time consuming and expensive to collect. Initializing the…

计算与语言 · 计算机科学 2020-10-12 Yinghui Huang , Hong-Kwang Kuo , Samuel Thomas , Zvi Kons , Kartik Audhkhasi , Brian Kingsbury , Ron Hoory , Michael Picheny

Emotional support (ES) systems alleviate users' mental distress by generating strategic supportive dialogues based on diverse user situations. However, ES systems are limited in their ability to generate effective ES dialogues that include…

计算与语言 · 计算机科学 2025-03-24 Shi Yin Hong , Uttamasha Oyshi , Quan Mai , Gibson Nkhata , Susan Gauch

Although end-to-end text-to-speech (TTS) models such as Tacotron have shown excellent results, they typically require a sizable set of high-quality <text, audio> pairs for training, which are expensive to collect. In this paper, we propose…

计算与语言 · 计算机科学 2018-08-31 Yu-An Chung , Yuxuan Wang , Wei-Ning Hsu , Yu Zhang , RJ Skerry-Ryan

We present a data-driven, end-to-end approach to transaction-based dialog systems that performs at near-human levels in terms of verbal response quality and factual grounding accuracy. We show that two essential components of the system…

计算与语言 · 计算机科学 2020-12-29 Bill Byrne , Karthik Krishnamoorthi , Saravanan Ganesh , Mihir Sanjay Kale

Human-like chatbots necessitate the use of commonsense reasoning in order to effectively comprehend and respond to implicit information present within conversations. Achieving such coherence and informativeness in responses, however, is a…

计算与语言 · 计算机科学 2023-10-24 Hyungjoo Chae , Yongho Song , Kai Tzu-iunn Ong , Taeyoon Kwon , Minjin Kim , Youngjae Yu , Dongha Lee , Dongyeop Kang , Jinyoung Yeo

End-to-end (E2E) speech-to-text translation (ST) often depends on pretraining its encoder and/or decoder using source transcripts via speech recognition or text translation tasks, without which translation performance drops substantially.…

计算与语言 · 计算机科学 2022-06-10 Biao Zhang , Barry Haddow , Rico Sennrich

Empathetic interaction is a cornerstone of human-machine communication, due to the need for understanding speech enriched with paralinguistic cues and generating emotional and expressive responses. However, the most powerful empathetic…

计算与语言 · 计算机科学 2025-10-28 Chen Wang , Tianyu Peng , Wen Yang , Yinan Bai , Guangfu Wang , Jun Lin , Lanpeng Jia , Lingxiang Wu , Jinqiao Wang , Chengqing Zong , Jiajun Zhang

End-to-end task-oriented dialogue (TOD) systems have achieved promising performance by leveraging sophisticated natural language understanding and natural language generation capabilities of pre-trained models. This work enables the TOD…

计算与语言 · 计算机科学 2023-08-17 Jianguo Zhang , Stephen Roller , Kun Qian , Zhiwei Liu , Rui Meng , Shelby Heinecke , Huan Wang , Silvio Savarese , Caiming Xiong

Chain-of-Thought (CoT) and its variants have markedly advanced the reasoning abilities of Large Language Models (LLMs), yet their monolithic and auto-regressive architecture inherently conflates high-level strategic planning with low-level…

机器学习 · 计算机科学 2025-10-01 Kaisen Yang , Lixuan He , Rushi Shah , Kaicheng Yang , Qinwei Ma , Dianbo Liu , Alex Lamb

We propose Machines Talking To Machines (M2M), a framework combining automation and crowdsourcing to rapidly bootstrap end-to-end dialogue agents for goal-oriented dialogues in arbitrary domains. M2M scales to new tasks with just a task…

人工智能 · 计算机科学 2018-01-16 Pararth Shah , Dilek Hakkani-Tür , Gokhan Tür , Abhinav Rastogi , Ankur Bapna , Neha Nayak , Larry Heck

Advances in machine learning have made it possible to perform various text and speech processing tasks, such as automatic speech recognition (ASR), in an end-to-end (E2E) manner. E2E approaches utilizing pre-trained models are gaining…

音频与语音处理 · 电气工程与系统科学 2024-06-07 Yukiya Hono , Koh Mitsuda , Tianyu Zhao , Kentaro Mitsui , Toshiaki Wakatsuki , Kei Sawada

Large-scale pre-training has shown remarkable performance in building open-domain dialogue systems. However, previous works mainly focus on showing and evaluating the conversational performance of the released dialogue model, ignoring the…

计算与语言 · 计算机科学 2023-10-24 Yuxian Gu , Jiaxin Wen , Hao Sun , Yi Song , Pei Ke , Chujie Zheng , Zheng Zhang , Jianzhu Yao , Lei Liu , Xiaoyan Zhu , Minlie Huang

Natural language understanding and dialogue policy learning are both essential in conversational systems that predict the next system actions in response to a current user utterance. Conventional approaches aggregate separate models of…

计算与语言 · 计算机科学 2017-10-03 Xuesong Yang , Yun-Nung Chen , Dilek Hakkani-Tur , Paul Crook , Xiujun Li , Jianfeng Gao , Li Deng

Task-oriented dialogue (ToD) benchmarks provide an important avenue to measure progress and develop better conversational agents. However, existing datasets for end-to-end ToD modeling are limited to a single language, hindering the…

计算与语言 · 计算机科学 2021-06-08 Zhaojiang Lin , Andrea Madotto , Genta Indra Winata , Peng Xu , Feijun Jiang , Yuxiang Hu , Chen Shi , Pascale Fung

Modern text-to-speech (TTS) systems are able to generate audio that sounds almost as natural as human speech. However, the bar of developing high-quality TTS systems remains high since a sizable set of studio-quality <text, audio> pairs is…

计算与语言 · 计算机科学 2019-06-19 Wei Fang , Yu-An Chung , James Glass

Full-duplex spoken dialogue systems significantly surpass traditional turn-based dialogue systems, as they allow simultaneous bidirectional communication, closely mirroring human-human interactions. However, achieving low latency and…

计算与语言 · 计算机科学 2025-01-06 Qinglin Zhang , Luyao Cheng , Chong Deng , Qian Chen , Wen Wang , Siqi Zheng , Jiaqing Liu , Hai Yu , Chaohong Tan , Zhihao Du , Shiliang Zhang

Large Language Models (LLMs) excel at reasoning and planning when trained on chainof-thought (CoT) data, where the step-by-step thought process is explicitly outlined by text tokens. However, this results in lengthy inputs where many words…

计算与语言 · 计算机科学 2025-09-03 DiJia Su , Hanlin Zhu , Yingchen Xu , Jiantao Jiao , Yuandong Tian , Qinqing Zheng

Chain-of-Thought (CoT) is widely applied to enhance the LLM capability in math, coding and reasoning tasks. However, its performance is limited for open-domain tasks, when there are no clearly defined reasoning steps or logical transitions.…

计算与语言 · 计算机科学 2025-11-18 Qingqing Gu , Dan Wang , Yue Zhao , Xiaoyu Wang , Zhonglin Jiang , Yong Chen , Hongyan Li , Luo Ji