paper-with-me

Papers

Unsupervised Auditory and Semantic Entrainment Models with Deep Neural Networks

2023-12-22 · Jay Kejriwal, Stefan Benus, Lina M. Rojas-Barahona

Speakers tend to engage in adaptive behavior, known as entrainment, when they become similar to their interlocutor in various aspects of speaking. We present an unsupervised deep learning framework that derives meaningful representation from textual features for developing semantic entrainment. We investigate the model's performance by extracting features using different variations of the BERT model (DistilBERT and XLM-RoBERTa) and Google's universal sentence encoder (USE) embeddings on two human-human (HH) corpora (The Fisher Corpus English Part 1, Columbia games corpus) and one human-machine (HM) corpus (Voice Assistant Conversation Corpus (VACC)). In addition to semantic features we also trained DNN-based models utilizing two auditory embeddings (TRIpLet Loss network (TRILL) vectors, Low-level descriptors (LLD) features) and two units of analysis (Inter pausal unit and Turn). The results show that semantic entrainment can be assessed with our model, that models can distinguish between HH and HM interactions and that the two units of analysis for extracting acoustic features provide comparable findings.

📄 PDF Abstract BibTeX arXiv:2312.15098

Code (0)

등록된 구현이 없습니다.

Tasks

SentenceTriplet

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Relationship between auditory and semantic entrainment using Deep Neural Networks (DNN)

2023-12-27 · Jay Kejriwal, Štefan Beňuš

The tendency of people to engage in similar, matching, or synchronized behaviour when interacting is known as entrainment. Many studies examined linguistic (syntactic and lexical structures) and paralinguistic (pitch, in…

Triplet

Towards an Unsupervised Entrainment Distance in Conversational Speech using Deep Neural Networks

2018-04-23 · Md Nasir, Brian Baucom, Shrikanth Narayanan, Panayiotis Georgiou

Entrainment is a known adaptation mechanism that causes interaction participants to adapt or synchronize their acoustic characteristics. Understanding how interlocutors tend to adapt to each other's speaking style throug…

Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs

2025-05-14 · Jingcheng Niu, Xingdi Yuan, Tong Wang, Hamidreza Saghir 외

We observe a novel phenomenon, contextual entrainment, across a wide range of language models (LMs) and prompt settings, providing a new mechanistic perspective on how LMs become distracted by ``irrelevant'' contextual i…

counterfactual

Single-word Auditory Attention Decoding Using Deep Learning Model

2024-10-15 · Nhan Duc Thanh Nguyen, Huy Phan, Kaare Mikkelsen, Preben Kidmose

Identifying auditory attention by comparing auditory stimuli and corresponding brain responses, is known as auditory attention decoding (AAD). The majority of AAD algorithms utilize the so-called envelope entrainment mec…

Deep LearningEEG

Better and Worse with Scale: How Contextual Entrainment Diverges with Model Size

2026-04-14 · Dikshant Kukreja, Kshitij Sah, Gautam Gupta, Avinash Anand 외 arxiv

Larger language models become simultaneously better and worse at handling contextual information -- better at ignoring false claims, worse at ignoring irrelevant tokens. We formalize this apparent paradox through the fir…