中文
相关论文

相关论文: From Independence to Interaction: Speaker-Aware Si…

200 篇论文

Neural network-based dialog systems are attracting increasing attention in both academia and industry. Recently, researchers have begun to realize the importance of speaker modeling in neural dialog systems, but there lacks established…

计算与语言 · 计算机科学 2018-10-01 Zhao Meng , Lili Mou , Zhi Jin

Speaker diarization systems often struggle with high intrinsic intra-speaker variability, such as shifts in emotion, health, or content. This can cause segments from the same speaker to be misclassified as different individuals, for…

音频与语音处理 · 电气工程与系统科学 2025-09-19 Miseul Kim , Soo Jin Park , Kyungguen Byun , Hyeon-Kyeong Shin , Sunkuk Moon , Shuhua Zhang , Erik Visser

Training agents to communicate with one another given task-based supervision only has attracted considerable attention recently, due to the growing interest in developing models for human-agent interaction. Prior work on the topic focused…

计算与语言 · 计算机科学 2019-03-26 Ben Bogin , Mor Geva , Jonathan Berant

Sequence-to-Sequence Text-to-Speech architectures that directly generate low level acoustic features from phonetic sequences are known to produce natural and expressive speech when provided with adequate amounts of training data. Such…

音频与语音处理 · 电气工程与系统科学 2022-07-26 Raul Fernandez , David Haws , Guy Lorberbom , Slava Shechtman , Alexander Sorin

In a human-machine dialog scenario, deciding the appropriate time for the machine to take the turn is an open research problem. In contrast, humans engaged in conversations are able to timely decide when to interrupt the speaker for…

计算与语言 · 计算机科学 2019-07-12 Andrei C. Coman , Koichiro Yoshino , Yukitoshi Murase , Satoshi Nakamura , Giuseppe Riccardi

Optimization of a trade-off between the number of speakers and their temporal variability (or session diversity) is crucial for the development of a speaker recognition system together with making the data collection process feasible from a…

音频与语音处理 · 电气工程与系统科学 2024-11-13 Anton Okhotnikov , Nikita Torgashov , Ivan Yakovlev , Pavel Malov , Rostislav Makarov

Multiturn dialogue models aim to generate human-like responses by leveraging conversational context, consisting of utterances from previous exchanges. Existing methods often neglect the interactions between these utterances or treat all of…

计算与语言 · 计算机科学 2025-04-15 Akanksha Mehndiratta , Krishna Asawa

Existing multi-channel continuous speech separation (CSS) models are heavily dependent on supervised data - either simulated data which causes data mismatch between the training and real-data testing, or the real transcribed overlapping…

音频与语音处理 · 电气工程与系统科学 2022-04-08 Xiaofei Wang , Dongmei Wang , Naoyuki Kanda , Sefik Emre Eskimez , Takuya Yoshioka

This paper investigates the application of voice activity projection (VAP), a predictive turn-taking model for spoken dialogue, on multilingual data, encompassing English, Mandarin, and Japanese. The VAP model continuously predicts the…

计算与语言 · 计算机科学 2024-03-18 Koji Inoue , Bing'er Jiang , Erik Ekstedt , Tatsuya Kawahara , Gabriel Skantze

Conversations between a clinician and a patient, in natural conditions, are valuable sources of information for medical follow-up. The automatic analysis of these dialogues could help extract new language markers and speed-up the…

We introduce proactive hearing assistants that automatically identify and separate the wearer's conversation partners, without requiring explicit prompts. Our system operates on egocentric binaural audio and uses the wearer's self-speech as…

计算与语言 · 计算机科学 2025-11-17 Guilin Hu , Malek Itani , Tuochao Chen , Shyamnath Gollakota

In human conversational interactions, turn-taking exchanges can be coordinated using cues from multiple modalities. To design spoken dialog systems that can conduct fluid interactions it is desirable to incorporate cues from separate…

计算与语言 · 计算机科学 2018-09-03 Matthew Roddy , Gabriel Skantze , Naomi Harte

Pause insertion, also known as phrase break prediction and phrasing, is an essential part of TTS systems because proper pauses with natural duration significantly enhance the rhythm and intelligibility of synthetic speech. However,…

音频与语音处理 · 电气工程与系统科学 2023-02-28 Dong Yang , Tomoki Koriyama , Yuki Saito , Takaaki Saeki , Detai Xin , Hiroshi Saruwatari

Since the first speech recognition systems were built more than 30 years ago, improvement in voice technology has enabled applications such as smart assistants and automated customer support. However, conversation intelligence of the future…

音频与语音处理 · 电气工程与系统科学 2024-02-15 Desh Raj

In this paper, we study the problem of employing pre-trained language models for multi-turn response selection in retrieval-based chatbots. A new model, named Speaker-Aware BERT (SA-BERT), is proposed in order to make the model aware of the…

计算与语言 · 计算机科学 2020-07-31 Jia-Chen Gu , Tianda Li , Quan Liu , Zhen-Hua Ling , Zhiming Su , Si Wei , Xiaodan Zhu

Testing conversational AI systems at scale across diverse domains necessitates realistic and diverse user interactions capturing a wide array of behavioral patterns. We present a novel multi-agent framework for realistic, explainable human…

人机交互 · 计算机科学 2026-01-23 Hareeshwar Karthikeyan

High-fidelity speech can be synthesized by end-to-end text-to-speech models in recent years. However, accessing and controlling speech attributes such as speaker identity, prosody, and emotion in a text-to-speech system remains a challenge.…

音频与语音处理 · 电气工程与系统科学 2020-08-05 Zexin Cai , Chuxiong Zhang , Ming Li

In human conversation, empathic dialogue requires nuanced temporal cues indicating whether the conversational partner is paying attention. This type of "active listening" is overlooked in the design of Conversational Agents (CAs), which use…

人机交互 · 计算机科学 2026-02-09 Zhihan Jiang , Qianhui Chen , Chu Zhang , Yanheng Li , Ray LC

This paper describes representations of time-dependent signals that are invariant under any invertible time-independent transformation of the signal time series. Such a representation is created by rescaling the signal in a non-linear…

计算与语言 · 计算机科学 2007-05-23 David N. Levin

The recent wave of audio foundation models (FMs) could provide new capabilities for conversational modeling. However, there have been limited efforts to evaluate these audio FMs comprehensively on their ability to have natural and…

计算与语言 · 计算机科学 2025-03-04 Siddhant Arora , Zhiyun Lu , Chung-Cheng Chiu , Ruoming Pang , Shinji Watanabe