Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"speech": models, code, and papers

Textual Paralanguage and its Implications for Marketing Communications

May 22, 2016
Andrea Webb Luangrath, Joann Peck, Victor A. Barger

Both face-to-face communication and communication in online environments convey information beyond the actual verbal message. In a traditional face-to-face conversation, paralanguage, or the ancillary meaning- and emotion-laden aspects of speech that are not actual verbal prose, gives contextual information that allows interactors to more appropriately understand the message being conveyed. In this paper, we conceptualize textual paralanguage (TPL), which we define as written manifestations of nonverbal audible, tactile, and visual elements that supplement or replace written language and that can be expressed through words, symbols, images, punctuation, demarcations, or any combination of these elements. We develop a typology of textual paralanguage using data from Twitter, Facebook, and Instagram. We present a conceptual framework of antecedents and consequences of brands' use of textual paralanguage. Implications for theory and practice are discussed.

* Journal of Consumer Psychology 27 (2017) 98-107 
* Forthcoming in the Journal of Consumer Psychology 

  Access Paper or Ask Questions

Dynamic Bayesian Multinets

Jan 16, 2013
Jeff A. Bilmes

In this work, dynamic Bayesian multinets are introduced where a Markov chain state at time t determines conditional independence patterns between random variables lying within a local time window surrounding t. It is shown how information-theoretic criterion functions can be used to induce sparse, discriminative, and class-conditional network structures that yield an optimal approximation to the class posterior probability, and therefore are useful for the classification task. Using a new structure learning heuristic, the resulting models are tested on a medium-vocabulary isolated-word speech recognition task. It is demonstrated that these discriminatively structured dynamic Bayesian multinets, when trained in a maximum likelihood setting using EM, can outperform both HMMs and other dynamic Bayesian networks with a similar number of parameters.

* Appears in Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence (UAI2000) 

  Access Paper or Ask Questions

StutterNet: Stuttering Detection Using Time Delay Neural Network

Jun 08, 2021
Shakeel A. Sheikh, Md Sahidullah, Fabrice Hirsch, Slim Ouni

This paper introduces StutterNet, a novel deep learning based stuttering detection capable of detecting and identifying various types of disfluencies. Most of the existing work in this domain uses automatic speech recognition (ASR) combined with language models for stuttering detection. Compared to the existing work, which depends on the ASR module, our method relies solely on the acoustic signal. We use a time-delay neural network (TDNN) suitable for capturing contextual aspects of the disfluent utterances. We evaluate our system on the UCLASS stuttering dataset consisting of more than 100 speakers. Our method achieves promising results and outperforms the state-of-the-art residual neural network based method. The number of trainable parameters of the proposed method is also substantially less due to the parameter sharing scheme of TDNN.

* Accepted in EUSIPCO 2021: European Signal Processing Conference 

  Access Paper or Ask Questions

Detecting Bot-Generated Text by Characterizing Linguistic Accommodation in Human-Bot Interactions

Jun 02, 2021
Paras Bhatt, Anthony Rios

Language generation models' democratization benefits many domains, from answering health-related questions to enhancing education by providing AI-driven tutoring services. However, language generation models' democratization also makes it easier to generate human-like text at-scale for nefarious activities, from spreading misinformation to targeting specific groups with hate speech. Thus, it is essential to understand how people interact with bots and develop methods to detect bot-generated text. This paper shows that bot-generated text detection methods are more robust across datasets and models if we use information about how people respond to it rather than using the bot's text directly. We also analyze linguistic alignment, providing insight into differences between human-human and human-bot conversations.

* 13 pages, to be published in Findings of ACL-IJCNLP 2021 

  Access Paper or Ask Questions

Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter

May 20, 2021
Wei Liu, Xiyan Fu, Yue Zhang, Wenming Xiao

Lexicon information and pre-trained models, such as BERT, have been combined to explore Chinese sequence labelling tasks due to their respective strengths. However, existing methods solely fuse lexicon features via a shallow and random initialized sequence layer and do not integrate them into the bottom layers of BERT. In this paper, we propose Lexicon Enhanced BERT (LEBERT) for Chinese sequence labelling, which integrates external lexicon knowledge into BERT layers directly by a Lexicon Adapter layer. Compared with the existing methods, our model facilitates deep lexicon knowledge fusion at the lower layers of BERT. Experiments on ten Chinese datasets of three tasks including Named Entity Recognition, Word Segmentation, and Part-of-Speech tagging, show that LEBERT achieves the state-of-the-art results.

* Accepted by ACL2021(Long Paper) 

  Access Paper or Ask Questions

Are Multilingual Models Effective in Code-Switching?

Mar 24, 2021
Genta Indra Winata, Samuel Cahyawijaya, Zihan Liu, Zhaojiang Lin, Andrea Madotto, Pascale Fung

Multilingual language models have shown decent performance in multilingual and cross-lingual natural language understanding tasks. However, the power of these multilingual models in code-switching tasks has not been fully explored. In this paper, we study the effectiveness of multilingual language models to understand their capability and adaptability to the mixed-language setting by considering the inference speed, performance, and number of parameters to measure their practicality. We conduct experiments in three language pairs on named entity recognition and part-of-speech tagging and compare them with existing methods, such as using bilingual embeddings and multilingual meta-embeddings. Our findings suggest that pre-trained multilingual models do not necessarily guarantee high-quality representations on code-switching, while using meta-embeddings achieves similar results with significantly fewer parameters.

  Access Paper or Ask Questions

How does Truth Evolve into Fake News? An Empirical Study of Fake News Evolution

Mar 10, 2021
Mingfei Guo, Xiuying Chen, Juntao Li, Dongyan Zhao, Rui Yan

Automatically identifying fake news from the Internet is a challenging problem in deception detection tasks. Online news is modified constantly during its propagation, e.g., malicious users distort the original truth and make up fake news. However, the continuous evolution process would generate unprecedented fake news and cheat the original model. We present the Fake News Evolution (FNE) dataset: a new dataset tracking the fake news evolution process. Our dataset is composed of 950 paired data, each of which consists of articles representing the three significant phases of the evolution process, which are the truth, the fake news, and the evolved fake news. We observe the features during the evolution and they are the disinformation techniques, text similarity, top 10 keywords, classification accuracy, parts of speech, and sentiment properties.

* The Web Conference 2021, Workshop on News Recommendation and Intelligence 
* 5 pages, 2 figures 

  Access Paper or Ask Questions

Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers

Feb 09, 2021
Shucong Zhang, Cong-Thanh Do, Rama Doddipatla, Erfan Loweimi, Peter Bell, Steve Renals

Although the lower layers of a deep neural network learn features which are transferable across datasets, these layers are not transferable within the same dataset. That is, in general, freezing the trained feature extractor (the lower layers) and retraining the classifier (the upper layers) on the same dataset leads to worse performance. In this paper, for the first time, we show that the frozen classifier is transferable within the same dataset. We develop a novel top-down training method which can be viewed as an algorithm for searching for high-quality classifiers. We tested this method on automatic speech recognition (ASR) tasks and language modelling tasks. The proposed method consistently improves recurrent neural network ASR models on Wall Street Journal, self-attention ASR models on Switchboard, and AWD-LSTM language models on WikiText-2.

* Accepted by ICASSP 2021 

  Access Paper or Ask Questions

droidlet: modular, heterogenous, multi-modal agents

Jan 25, 2021
Anurag Pratik, Soumith Chintala, Kavya Srinet, Dhiraj Gandhi, Rebecca Qian, Yuxuan Sun, Ryan Drew, Sara Elkafrawy, Anoushka Tiwari, Tucker Hart, Mary Williamson, Abhinav Gupta, Arthur Szlam

In recent years, there have been significant advances in building end-to-end Machine Learning (ML) systems that learn at scale. But most of these systems are: (a) isolated (perception, speech, or language only); (b) trained on static datasets. On the other hand, in the field of robotics, large-scale learning has always been difficult. Supervision is hard to gather and real world physical interactions are expensive. In this work we introduce and open-source droidlet, a modular, heterogeneous agent architecture and platform. It allows us to exploit both large-scale static datasets in perception and language and sophisticated heuristics often used in robotics; and provides tools for interactive annotation. Furthermore, it brings together perception, language and action onto one platform, providing a path towards agents that learn from the richness of real world interactions.

  Access Paper or Ask Questions