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

Adversarial Attacks against Neural Networks in Audio Domain: Exploiting Principal Components

Jul 14, 2020
Ken Alparslan, Yigit Alparslan, Matthew Burlick

Adversarial attacks are inputs that are similar to original inputs but altered on purpose. Speech-to-text neural networks that are widely used today are prone to misclassify adversarial attacks. In this study, first, we investigate the presence of targeted adversarial attacks by altering wave forms from Common Voice data set. We craft adversarial wave forms via Connectionist Temporal Classification Loss Function, and attack DeepSpeech, a speech-to-text neural network implemented by Mozilla. We achieve 100% adversarial success rate (zero successful classification by DeepSpeech) on all 25 adversarial wave forms that we crafted. Second, we investigate the use of PCA as a defense mechanism against adversarial attacks. We reduce dimensionality by applying PCA to these 25 attacks that we created and test them against DeepSpeech. We observe zero successful classification by DeepSpeech, which suggests PCA is not a good defense mechanism in audio domain. Finally, instead of using PCA as a defense mechanism, we use PCA this time to craft adversarial inputs under a black-box setting with minimal adversarial knowledge. With no knowledge regarding the model, parameters, or weights, we craft adversarial attacks by applying PCA to samples from Common Voice data set and achieve 100% adversarial success under black-box setting again when tested against DeepSpeech. We also experiment with different percentage of components necessary to result in a classification during attacking process. In all cases, adversary becomes successful.

* 8 pages, 14 figures 

  Access Paper or Ask Questions

A Target-Agnostic Attack on Deep Models: Exploiting Security Vulnerabilities of Transfer Learning

Apr 08, 2019
Shahbaz Rezaei, Xin Liu

Due to the lack of enough training data and high computational cost to train a deep neural network from scratch, transfer learning has been extensively used in many deep-neural-network-based applications, such as face recognition, image classification, speech recognition, etc. A commonly-used transfer learning approach involves taking a part of a pre-trained model, adding a few layers at the end, and re-training the new layers with a small dataset. This approach, while efficient and widely used, imposes a security vulnerability because the pre-trained models used in transfer learning are usually available publicly to everyone, including potential attackers. In this paper, we show that without any additional knowledge other than the pre-trained model, an attacker can launch an effective and efficient brute force attack that can craft instances of input to trigger each target class with high confidence. Note that we assume that the attacker does not have access to any target-specific information, including samples from target classes, re-trained model, and probabilities assigned by Softmax to each class, and thus called target-agnostic attack. These assumptions render all previous attacks impractical, to the best of our knowledge. To evaluate the proposed attack, we perform a set of experiments on face recognition and speech recognition tasks and show the effectiveness of the attack. Our work sheds light on a fundamental security challenge of transfer learning in deep neural networks.

  Access Paper or Ask Questions

GestureLens: Visual Analysis of Gestures in Presentation Videos

Apr 23, 2022
Haipeng Zeng, Xingbo Wang, Yong Wang, Aoyu Wu, Ting Chuen Pong, Huamin Qu

Appropriate gestures can enhance message delivery and audience engagement in both daily communication and public presentations. In this paper, we contribute a visual analytic approach that assists professional public speaking coaches in improving their practice of gesture training through analyzing presentation videos. Manually checking and exploring gesture usage in the presentation videos is often tedious and time-consuming. There lacks an efficient method to help users conduct gesture exploration, which is challenging due to the intrinsically temporal evolution of gestures and their complex correlation to speech content. In this paper, we propose GestureLens, a visual analytics system to facilitate gesture-based and content-based exploration of gesture usage in presentation videos. Specifically, the exploration view enables users to obtain a quick overview of the spatial and temporal distributions of gestures. The dynamic hand movements are firstly aggregated through a heatmap in the gesture space for uncovering spatial patterns, and then decomposed into two mutually perpendicular timelines for revealing temporal patterns. The relation view allows users to explicitly explore the correlation between speech content and gestures by enabling linked analysis and intuitive glyph designs. The video view and dynamic view show the context and overall dynamic movement of the selected gestures, respectively. Two usage scenarios and expert interviews with professional presentation coaches demonstrate the effectiveness and usefulness of GestureLens in facilitating gesture exploration and analysis of presentation videos.

* 14 pages, 6 figures. A preprint version of a publication at IEEE Transactions on Visualization and Computer Graphics (TVCG), 2022 

  Access Paper or Ask Questions

Voice activity detection in the wild: A data-driven approach using teacher-student training

May 10, 2021
Heinrich Dinkel, Shuai Wang, Xuenan Xu, Mengyue Wu, Kai Yu

Voice activity detection is an essential pre-processing component for speech-related tasks such as automatic speech recognition (ASR). Traditional supervised VAD systems obtain frame-level labels from an ASR pipeline by using, e.g., a Hidden Markov model. These ASR models are commonly trained on clean and fully transcribed data, limiting VAD systems to be trained on clean or synthetically noised datasets. Therefore, a major challenge for supervised VAD systems is their generalization towards noisy, real-world data. This work proposes a data-driven teacher-student approach for VAD, which utilizes vast and unconstrained audio data for training. Unlike previous approaches, only weak labels during teacher training are required, enabling the utilization of any real-world, potentially noisy dataset. Our approach firstly trains a teacher model on a source dataset (Audioset) using clip-level supervision. After training, the teacher provides frame-level guidance to a student model on an unlabeled, target dataset. A multitude of student models trained on mid- to large-sized datasets are investigated (Audioset, Voxceleb, NIST SRE). Our approach is then respectively evaluated on clean, artificially noised, and real-world data. We observe significant performance gains in artificially noised and real-world scenarios. Lastly, we compare our approach against other unsupervised and supervised VAD methods, demonstrating our method's superiority.

* IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 29, pp. 1542-1555, 2021 

  Access Paper or Ask Questions

Style Variation as a Vantage Point for Code-Switching

May 01, 2020
Khyathi Raghavi Chandu, Alan W Black

Code-Switching (CS) is a common phenomenon observed in several bilingual and multilingual communities, thereby attaining prevalence in digital and social media platforms. This increasing prominence demands the need to model CS languages for critical downstream tasks. A major problem in this domain is the dearth of annotated data and a substantial corpora to train large scale neural models. Generating vast amounts of quality text assists several down stream tasks that heavily rely on language modeling such as speech recognition, text-to-speech synthesis etc,. We present a novel vantage point of CS to be style variations between both the participating languages. Our approach does not need any external annotations such as lexical language ids. It mainly relies on easily obtainable monolingual corpora without any parallel alignment and a limited set of naturally CS sentences. We propose a two-stage generative adversarial training approach where the first stage generates competitive negative examples for CS and the second stage generates more realistic CS sentences. We present our experiments on the following pairs of languages: Spanish-English, Mandarin-English, Hindi-English and Arabic-French. We show that the trends in metrics for generated CS move closer to real CS data in each of the above language pairs through the dual stage training process. We believe this viewpoint of CS as style variations opens new perspectives for modeling various tasks in CS text.

  Access Paper or Ask Questions

Multi-scale Geometric Summaries for Similarity-based Sensor Fusion

Oct 13, 2018
Christopher J. Tralie, Paul Bendich, John Harer

In this work, we address fusion of heterogeneous sensor data using wavelet-based summaries of fused self-similarity information from each sensor. The technique we develop is quite general, does not require domain specific knowledge or physical models, and requires no training. Nonetheless, it can perform surprisingly well at the general task of differentiating classes of time-ordered behavior sequences which are sensed by more than one modality. As a demonstration of our capabilities in the audio to video context, we focus on the differentiation of speech sequences. Data from two or more modalities first are represented using self-similarity matrices(SSMs) corresponding to time-ordered point clouds in feature spaces of each of these data sources; we note that these feature spaces can be of entirely different scale and dimensionality. A fused similarity template is then derived from the modality-specific SSMs using a technique called similarity network fusion (SNF). We investigate pipelines using SNF as both an upstream (feature-level) and a downstream (ranking-level) fusion technique. Multiscale geometric features of this template are then extracted using a recently-developed technique called the scattering transform, and these features are then used to differentiate speech sequences. This method outperforms unsupervised techniques which operate directly on the raw data, and it also outperforms stovepiped methods which operate on SSMs separately derived from the distinct modalities. The benefits of this method become even more apparent as the simulated peak signal to noise ratio decreases.

* 9 pages, 13 Figures 

  Access Paper or Ask Questions

A Sparse Non-negative Matrix Factorization Framework for Identifying Functional Units of Tongue Behavior from MRI

Sep 29, 2018
Jonghye Woo, Jerry L. Prince, Maureen Stone, Fangxu Xing, Arnold Gomez, Jordan R. Green, Christopher J. Hartnick, Thomas J. Brady, Timothy G. Reese, Van J. Wedeen, Georges El Fakhri

Muscle coordination patterns of lingual behaviors are synergies generated by deforming local muscle groups in a variety of ways. Functional units are functional muscle groups of local structural elements within the tongue that compress, expand, and move in a cohesive and consistent manner. Identifying the functional units using tagged-Magnetic Resonance Imaging (MRI) sheds light on the mechanisms of normal and pathological muscle coordination patterns, yielding improvement in surgical planning, treatment, or rehabilitation procedures. Here, to mine this information, we propose a matrix factorization and probabilistic graphical model framework to produce building blocks and their associated weighting map using motion quantities extracted from tagged-MRI. Our tagged-MRI imaging and accurate voxel-level tracking provide previously unavailable internal tongue motion patterns, thus revealing the inner workings of the tongue during speech or other lingual behaviors. We then employ spectral clustering on the weighting map to identify the cohesive regions defined by the tongue motion that may involve multiple or undocumented regions. To evaluate our method, we perform a series of experiments. We first use two-dimensional images and synthetic data to demonstrate the accuracy of our method. We then use three-dimensional synthetic and \textit{in vivo} tongue motion data using protrusion and simple speech tasks to identify subject-specific and data-driven functional units of the tongue in localized regions.

* Accepted at IEEE TMI (

  Access Paper or Ask Questions

WEMAC: Women and Emotion Multi-modal Affective Computing dataset

Mar 01, 2022
Jose A. Miranda, Esther Rituerto-González, Laura Gutiérrez-Martín, Clara Luis-Mingueza, Manuel F. Canabal, Alberto Ramírez Bárcenas, Jose M. Lanza-Gutiérrez, Carmen Peláez-Moreno, Celia López-Ongil

Among the seventeen Sustainable Development Goals (SDGs) proposed within the 2030 Agenda and adopted by all the United Nations member states, the Fifth SDG is a call for action to turn Gender Equality into a fundamental human right and an essential foundation for a better world. It includes the eradication of all types of violence against women. Within this context, the UC3M4Safety research team aims to develop Bindi. This is a cyber-physical system which includes embedded Artificial Intelligence algorithms, for user real-time monitoring towards the detection of affective states, with the ultimate goal of achieving the early detection of risk situations for women. On this basis, we make use of wearable affective computing including smart sensors, data encryption for secure and accurate collection of presumed crime evidence, as well as the remote connection to protecting agents. Towards the development of such system, the recordings of different laboratory and into-the-wild datasets are in process. These are contained within the UC3M4Safety Database. Thus, this paper presents and details the first release of WEMAC, a novel multi-modal dataset, which comprises a laboratory-based experiment for 47 women volunteers that were exposed to validated audio-visual stimuli to induce real emotions by using a virtual reality headset while physiological, speech signals and self-reports were acquired and collected. We believe this dataset will serve and assist research on multi-modal affective computing using physiological and speech information.

  Access Paper or Ask Questions

EmoWrite: A Sentiment Analysis-Based Thought to Text Conversion

Mar 03, 2021
A. Shahid, I. Raza, S. A. Hussain

Brain Computer Interface (BCI) helps in processing and extraction of useful information from the acquired brain signals having applications in diverse fields such as military, medicine, neuroscience, and rehabilitation. BCI has been used to support paralytic patients having speech impediments with severe disabilities. To help paralytic patients communicate with ease, BCI based systems convert silent speech (thoughts) to text. However, these systems have an inconvenient graphical user interface, high latency, limited typing speed, and low accuracy rate. Apart from these limitations, the existing systems do not incorporate the inevitable factor of a patient's emotional states and sentiment analysis. The proposed system EmoWrite implements a dynamic keyboard with contextualized appearance of characters reducing the traversal time and improving the utilization of the screen space. The proposed system has been evaluated and compared with the existing systems for accuracy, convenience, sentimental analysis, and typing speed. This system results in 6.58 Words Per Minute (WPM) and 31.92 Characters Per Minute (CPM) with an accuracy of 90.36 percent. EmoWrite also gives remarkable results when it comes to the integration of emotional states. Its Information Transfer Rate (ITR) is also high as compared to other systems i.e., 87.55 bits per min with commands and 72.52 bits per min for letters. Furthermore, it provides easy to use interface with a latency of 2.685 sec.

  Access Paper or Ask Questions