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

Automatically Neutralizing Subjective Bias in Text

Dec 12, 2019
Reid Pryzant, Richard Diehl Martinez, Nathan Dass, Sadao Kurohashi, Dan Jurafsky, Diyi Yang

Texts like news, encyclopedias, and some social media strive for objectivity. Yet bias in the form of inappropriate subjectivity - introducing attitudes via framing, presupposing truth, and casting doubt - remains ubiquitous. This kind of bias erodes our collective trust and fuels social conflict. To address this issue, we introduce a novel testbed for natural language generation: automatically bringing inappropriately subjective text into a neutral point of view ("neutralizing" biased text). We also offer the first parallel corpus of biased language. The corpus contains 180,000 sentence pairs and originates from Wikipedia edits that removed various framings, presuppositions, and attitudes from biased sentences. Last, we propose two strong encoder-decoder baselines for the task. A straightforward yet opaque CONCURRENT system uses a BERT encoder to identify subjective words as part of the generation process. An interpretable and controllable MODULAR algorithm separates these steps, using (1) a BERT-based classifier to identify problematic words and (2) a novel join embedding through which the classifier can edit the hidden states of the encoder. Large-scale human evaluation across four domains (encyclopedias, news headlines, books, and political speeches) suggests that these algorithms are a first step towards the automatic identification and reduction of bias.

* To appear at AAAI 2020 

  Access Paper or Ask Questions

Forward-Backward Decoding for Regularizing End-to-End TTS

Jul 18, 2019
Yibin Zheng, Xi Wang, Lei He, Shifeng Pan, Frank K. Soong, Zhengqi Wen, Jianhua Tao

Neural end-to-end TTS can generate very high-quality synthesized speech, and even close to human recording within similar domain text. However, it performs unsatisfactory when scaling it to challenging test sets. One concern is that the encoder-decoder with attention-based network adopts autoregressive generative sequence model with the limitation of "exposure bias" To address this issue, we propose two novel methods, which learn to predict future by improving agreement between forward and backward decoding sequence. The first one is achieved by introducing divergence regularization terms into model training objective to reduce the mismatch between two directional models, namely L2R and R2L (which generates targets from left-to-right and right-to-left, respectively). While the second one operates on decoder-level and exploits the future information during decoding. In addition, we employ a joint training strategy to allow forward and backward decoding to improve each other in an interactive process. Experimental results show our proposed methods especially the second one (bidirectional decoder regularization), leads a significantly improvement on both robustness and overall naturalness, as outperforming baseline (the revised version of Tacotron2) with a MOS gap of 0.14 in a challenging test, and achieving close to human quality (4.42 vs. 4.49 in MOS) on general test.

* Accepted by INTERSPEECH2019. arXiv admin note: text overlap with arXiv:1808.04064, arXiv:1804.05374 by other authors 

  Access Paper or Ask Questions

Spoof detection using x-vector and feature switching

Apr 16, 2019
Mari Ganesh Kumar, Suvidha Rupesh Kumar, Saranya M, B. Bharathi, Hema A. Murthy

Detecting spoofed utterances is a fundamental problem in voice-based biometrics. Spoofing can be performed either by logical accesses like speech synthesis, voice conversion or by physical accesses such as replaying the pre-recorded utterance. Inspired by the state-of-the-art x-vector based speaker verification approach, this paper proposes a deep neural network (DNN) architecture for spoof detection from both logical and physical access. A novelty of the x-vector approach vis-a-vis conventional DNN based systems is that it can handle variable length utterances during testing. Performance of the proposed x-vector systems and the baseline Gaussian mixture model (GMM) systems is analyzed on the ASV-spoof-2019 dataset. The proposed system surpasses the GMM system for physical access, whereas the GMM system detects logical access better. Compared to the GMM systems, the proposed x-vector approach gives an average relative improvement of 14.64% for physical access. When combined with the decision-level feature switching (DLFS) paradigm, the best system in the proposed approach outperforms the best baseline systems with a relative improvement of 67.48% and 40.04% for both logical and physical access in terms of minimum tandem cost detection function (min-t-DCF), respectively.


  Access Paper or Ask Questions

Dialogue Act Segmentation for Vietnamese Human-Human Conversational Texts

Aug 16, 2017
Thi Lan Ngo, Khac Linh Pham, Minh Son Cao, Son Bao Pham, Xuan Hieu Phan

Dialog act identification plays an important role in understanding conversations. It has been widely applied in many fields such as dialogue systems, automatic machine translation, automatic speech recognition, and especially useful in systems with human-computer natural language dialogue interfaces such as virtual assistants and chatbots. The first step of identifying dialog act is identifying the boundary of the dialog act in utterances. In this paper, we focus on segmenting the utterance according to the dialog act boundaries, i.e. functional segments identification, for Vietnamese utterances. We investigate carefully functional segment identification in two approaches: (1) machine learning approach using maximum entropy (ME) and conditional random fields (CRFs); (2) deep learning approach using bidirectional Long Short-Term Memory (LSTM) with a CRF layer (Bi-LSTM-CRF) on two different conversational datasets: (1) Facebook messages (Message data); (2) transcription from phone conversations (Phone data). To the best of our knowledge, this is the first work that applies deep learning based approach to dialog act segmentation. As the results show, deep learning approach performs appreciably better as to compare with traditional machine learning approaches. Moreover, it is also the first study that tackles dialog act and functional segment identification for Vietnamese.

* 6 pages, 2 figures 

  Access Paper or Ask Questions

Simple Black-Box Adversarial Perturbations for Deep Networks

Dec 19, 2016
Nina Narodytska, Shiva Prasad Kasiviswanathan

Deep neural networks are powerful and popular learning models that achieve state-of-the-art pattern recognition performance on many computer vision, speech, and language processing tasks. However, these networks have also been shown susceptible to carefully crafted adversarial perturbations which force misclassification of the inputs. Adversarial examples enable adversaries to subvert the expected system behavior leading to undesired consequences and could pose a security risk when these systems are deployed in the real world. In this work, we focus on deep convolutional neural networks and demonstrate that adversaries can easily craft adversarial examples even without any internal knowledge of the target network. Our attacks treat the network as an oracle (black-box) and only assume that the output of the network can be observed on the probed inputs. Our first attack is based on a simple idea of adding perturbation to a randomly selected single pixel or a small set of them. We then improve the effectiveness of this attack by carefully constructing a small set of pixels to perturb by using the idea of greedy local-search. Our proposed attacks also naturally extend to a stronger notion of misclassification. Our extensive experimental results illustrate that even these elementary attacks can reveal a deep neural network's vulnerabilities. The simplicity and effectiveness of our proposed schemes mean that they could serve as a litmus test for designing robust networks.

* 19 Pages 

  Access Paper or Ask Questions

Captcha Attack: Turning Captchas Against Humanity

Jan 13, 2022
Mauro Conti, Luca Pajola, Pier Paolo Tricomi

Nowadays, people generate and share massive content on online platforms (e.g., social networks, blogs). In 2021, the 1.9 billion daily active Facebook users posted around 150 thousand photos every minute. Content moderators constantly monitor these online platforms to prevent the spreading of inappropriate content (e.g., hate speech, nudity images). Based on deep learning (DL) advances, Automatic Content Moderators (ACM) help human moderators handle high data volume. Despite their advantages, attackers can exploit weaknesses of DL components (e.g., preprocessing, model) to affect their performance. Therefore, an attacker can leverage such techniques to spread inappropriate content by evading ACM. In this work, we propose CAPtcha Attack (CAPA), an adversarial technique that allows users to spread inappropriate text online by evading ACM controls. CAPA, by generating custom textual CAPTCHAs, exploits ACM's careless design implementations and internal procedures vulnerabilities. We test our attack on real-world ACM, and the results confirm the ferocity of our simple yet effective attack, reaching up to a 100% evasion success in most cases. At the same time, we demonstrate the difficulties in designing CAPA mitigations, opening new challenges in CAPTCHAs research area.

* Currently under submission 

  Access Paper or Ask Questions

Captcha Attack:Turning Captchas Against Humanity

Jan 11, 2022
Mauro Conti, Luca Pajola, Pier Paolo Tricomi

Nowadays, people generate and share massive content on online platforms (e.g., social networks, blogs). In 2021, the 1.9 billion daily active Facebook users posted around 150 thousand photos every minute. Content moderators constantly monitor these online platforms to prevent the spreading of inappropriate content (e.g., hate speech, nudity images). Based on deep learning (DL) advances, Automatic Content Moderators (ACM) help human moderators handle high data volume. Despite their advantages, attackers can exploit weaknesses of DL components (e.g., preprocessing, model) to affect their performance. Therefore, an attacker can leverage such techniques to spread inappropriate content by evading ACM. In this work, we propose CAPtcha Attack (CAPA), an adversarial technique that allows users to spread inappropriate text online by evading ACM controls. CAPA, by generating custom textual CAPTCHAs, exploits ACM's careless design implementations and internal procedures vulnerabilities. We test our attack on real-world ACM, and the results confirm the ferocity of our simple yet effective attack, reaching up to a 100% evasion success in most cases. At the same time, we demonstrate the difficulties in designing CAPA mitigations, opening new challenges in CAPTCHAs research area.

* Currently under submission 

  Access Paper or Ask Questions

Using Sampling to Estimate and Improve Performance of Automated Scoring Systems with Guarantees

Nov 17, 2021
Yaman Kumar Singla, Sriram Krishna, Rajiv Ratn Shah, Changyou Chen

Automated Scoring (AS), the natural language processing task of scoring essays and speeches in an educational testing setting, is growing in popularity and being deployed across contexts from government examinations to companies providing language proficiency services. However, existing systems either forgo human raters entirely, thus harming the reliability of the test, or score every response by both human and machine thereby increasing costs. We target the spectrum of possible solutions in between, making use of both humans and machines to provide a higher quality test while keeping costs reasonable to democratize access to AS. In this work, we propose a combination of the existing paradigms, sampling responses to be scored by humans intelligently. We propose reward sampling and observe significant gains in accuracy (19.80% increase on average) and quadratic weighted kappa (QWK) (25.60% on average) with a relatively small human budget (30% samples) using our proposed sampling. The accuracy increase observed using standard random and importance sampling baselines are 8.6% and 12.2% respectively. Furthermore, we demonstrate the system's model agnostic nature by measuring its performance on a variety of models currently deployed in an AS setting as well as pseudo models. Finally, we propose an algorithm to estimate the accuracy/QWK with statistical guarantees (Our code is available at https://git.io/J1IOy).


  Access Paper or Ask Questions

<<
799
800
801
802
803
804
805
806
807
808
809
810
811
>>