Listener response

Xudong, Deng

doi:10.1075/hoph.4.07xud

Cited by 9 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The aforementioned predictors have only considered backchanneling as a binary decision (absence vs presence), a lumping approach [39,27] where all types of BCs are considered as a single one and the focus is on finding right time opportunities for a BCs in the speaker's talk.…”

Section: Related Workmentioning

confidence: 99%

“…On the other hand, the splitting approach [39] examines discrete and specific BC responses. In alignment to the splitting approach, some predictors have taken the task to a more fined BC granularity.…”

Section: Related Workmentioning

confidence: 99%

“…where within the speaker's speech the BCs occur [33]. On the other hand, the splitting approach aims at explaining BC functionalities and categorizing them according to their type, function and discrete specific responses [39].…”

Section: Introductionmentioning

confidence: 99%

“…BCs have been categorized under different paradigms [6,12,29]. On the one hand, the lumping approach [39,27] focuses on BC placement, i.e. where within the speaker's speech the BCs occur [33].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

OH, JEEZ! or UH-HUH? A Listener-Aware Backchannel Predictor on ASR Transcriptions

Ortega

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This paper presents our latest investigation on modeling backchannel in conversations. Motivated by a proactive backchanneling theory, we aim at developing a system which acts as a proactive listener by inserting backchannels, such as continuers and assessment, to influence speakers. Our model takes into account not only lexical and acoustic cues, but also introduces the simple and novel idea of using listener embeddings to mimic different backchanneling behaviours. Our experimental results on the Switchboard benchmark dataset reveal that acoustic cues are more important than lexical cues in this task and their combination with listener embeddings works best on both, manual transcriptions and automatically generated transcriptions.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

OH, JEEZ! or UH-HUH? A Listener-Aware Backchannel Predictor on ASR Transcriptions

Ortega

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…‘Minimal responses’ are a primary means of displaying listening. Scholars have used different terminologies to describe them (see Fujimoto, 2007; Xudong, 2009). Fellegy (1995: 186) identifies minimal responses as utterances such as ‘mmhmm’, ‘yeah’, ‘uh-huh’ and ‘right’, used by a listener during a speech event to signal a certain level of engagement with a speaker.…”

Section: Listenership: Theoretical Backgroundmentioning

confidence: 99%

Type your listenership: An exploration of listenership in instant messages

Choe

2018

Discourse Studies

View full text Add to dashboard Cite

This case study investigates how people ‘listen’ and act as ‘listeners’ in instant messages. Little research has been done on listenership and listeners in text-based digital discourse; to address this gap, I analyze a group instant message conversation among five Korean young women via KakaoTalk, a free instant messaging application. Demonstrating previous studies on listenership and listeners in spoken discourse and defining ‘listenership’ as the act of giving feedback on prior messages, I identify and explicate four ways of showing listenership in instant message interaction: (1) minimal responses, (2) machine gun listenership, (3) laughing and (4) sticker reaction. My analysis illuminates how verbal and non-verbal forms of listenership are adapted to typed-based online contexts as well as how listenership contributes to the construction of talk in typed-based digital environments.

show abstract

Backchannels: Quantity, Type and Timing Matters

Poppe

Truong

Heylen

2011

Intelligent Virtual Agents

View full text Add to dashboard Cite

Abstract. In a perception experiment, we systematically varied the quantity, type and timing of backchannels. Participants viewed stimuli of a real speaker side-by-side with an animated listener and rated how human-like they perceived the latter's backchannel behavior. In addition, we obtained measures of appropriateness and optionality for each backchannel from key strokes. This approach allowed us to analyze the influence of each of the factors on entire fragments and on individual backchannels. The originally performed type and timing of a backchannel appeared to be more human-like, compared to a switched type or random timing. In addition, we found that nods are more often appropriate than vocalizations. For quantity, too few or too many backchannels per minute appeared to reduce the quality of the behavior. These findings are important for the design of algorithms for the automatic generation of backchannel behavior for artificial listeners.

show abstract

Listener response

Cited by 9 publications

References 0 publications

OH, JEEZ! or UH-HUH? A Listener-Aware Backchannel Predictor on ASR Transcriptions

OH, JEEZ! or UH-HUH? A Listener-Aware Backchannel Predictor on ASR Transcriptions

Type your listenership: An exploration of listenership in instant messages

Backchannels: Quantity, Type and Timing Matters

Contact Info

Product

Resources

About