arXiv subjects

Shrikanth Narayanan

Publications and source records attributed to Shrikanth Narayanan.

At least 181 records · Page 10Linked to original sources

arXiv2021

Speaker-invariant Affective Representation Learning via Adversarial Training

Representation learning for speech emotion recognition is challenging due to labeled data sparsity issue and lack of gold standard references. In addition, there is much variability from input speech signals, human subjective perception of the signals and emotion label ambiguity. In this paper, we propose a machine learning framework to obtain speech emotion representations by limiting the effect of speaker variability in the speech signals. Specifically, we propose to disentangle the speaker characteristics from emotion through an adversarial training network in order to better represent emotion. Our method combines the gradient reversal technique with an entropy loss function to remove such speaker information. Our approach is evaluated on both IEMOCAP and CMU-MOSEI datasets. We show that our method improves speech emotion classification and increases generalization to unseen speakers.

eess.AS↗

arXiv2021

Perceptual-based deep-learning denoiser as a defense against adversarial attacks on ASR systems

In this paper we investigate speech denoising as a defense against adversarial attacks on automatic speech recognition (ASR) systems. Adversarial attacks attempt to force misclassification by adding small perturbations to the original speech signal. We propose to counteract this by employing a neural-network based denoiser as a pre-processor in the ASR pipeline. The denoiser is independent of the downstream ASR model, and thus can be rapidly deployed in existing systems. We found that training the denoisier using a perceptually motivated loss function resulted in increased adversarial robustness without compromising ASR performance on benign samples. Our defense was evaluated (as a part of the DARPA GARD program) on the 'Kenansville' attack strategy across a range of attack strengths and speech samples. An average improvement in Word Error Rate (WER) of about 7.7% was observed over the undefended model at 20 dB signal-to-noise-ratio (SNR) attack strength.

eess.AS↗

arXiv2021

Acted vs. Improvised: Domain Adaptation for Elicitation Approaches in Audio-Visual Emotion Recognition

Key challenges in developing generalized automatic emotion recognition systems include scarcity of labeled data and lack of gold-standard references. Even for the cues that are labeled as the same emotion category, the variability of associated expressions can be high depending on the elicitation context e.g., emotion elicited during improvised conversations vs. acted sessions with predefined scripts. In this work, we regard the emotion elicitation approach as domain knowledge, and explore domain transfer learning techniques on emotional utterances collected under different emotion elicitation approaches, particularly with limited labeled target samples. Our emotion recognition model combines the gradient reversal technique with an entropy loss function as well as the softlabel loss, and the experiment results show that domain transfer learning methods can be employed to alleviate the domain mismatch between different elicitation approaches. Our work provides new insights into emotion data collection, particularly the impact of its elicitation strategies, and the importance of domain adaptation in emotion recognition aiming for generalized systems.

cs.SD↗

arXiv2021

Unsupervised Speech Representation Learning for Behavior Modeling using Triplet Enhanced Contextualized Networks

Speech encodes a wealth of information related to human behavior and has been used in a variety of automated behavior recognition tasks. However, extracting behavioral information from speech remains challenging including due to inadequate training data resources stemming from the often low occurrence frequencies of specific behavioral patterns. Moreover, supervised behavioral modeling typically relies on domain-specific construct definitions and corresponding manually-annotated data, rendering generalizing across domains challenging. In this paper, we exploit the stationary properties of human behavior within an interaction and present a representation learning method to capture behavioral information from speech in an unsupervised way. We hypothesize that nearby segments of speech share the same behavioral context and hence map onto similar underlying behavioral representations. We present an encoder-decoder based Deep Contextualized Network (DCN) as well as a Triplet-Enhanced DCN (TE-DCN) framework to capture the behavioral context and derive a manifold representation, where speech frames with similar behaviors are closer while frames of different behaviors maintain larger distances. The models are trained on movie audio data and validated on diverse domains including on a couples therapy corpus and other publicly collected data (e.g., stand-up comedy). With encouraging results, our proposed framework shows the feasibility of unsupervised learning within cross-domain behavioral modeling.

eess.AS↗

arXiv2021

Automated Evaluation Of Psychotherapy Skills Using Speech And Language Technologies

With the growing prevalence of psychological interventions, it is vital to have measures which rate the effectiveness of psychological care to assist in training, supervision, and quality assurance of services. Traditionally, quality assessment is addressed by human raters who evaluate recorded sessions along specific dimensions, often codified through constructs relevant to the approach and domain. This is however a cost-prohibitive and time-consuming method that leads to poor feasibility and limited use in real-world settings. To facilitate this process, we have developed an automated competency rating tool able to process the raw recorded audio of a session, analyzing who spoke when, what they said, and how the health professional used language to provide therapy. Focusing on a use case of a specific type of psychotherapy called Motivational Interviewing, our system gives comprehensive feedback to the therapist, including information about the dynamics of the session (e.g., therapist's vs. client's talking time), low-level psychological language descriptors (e.g., type of questions asked), as well as other high-level behavioral constructs (e.g., the extent to which the therapist understands the clients' perspective). We describe our platform and its performance using a dataset of more than 5,000 recordings drawn from its deployment in a real-world clinical setting used to assist training of new therapists. Widespread use of automated psychotherapy rating tools may augment experts' capabilities by providing an avenue for more effective training and skill improvement, eventually leading to more positive clinical outcomes.

eess.AS↗

arXiv2021

Evidence of Task-Independent Person-Specific Signatures in EEG using Subspace Techniques

Electroencephalography (EEG) signals are promising as alternatives to other biometrics owing to their protection against spoofing. Previous studies have focused on capturing individual variability by analyzing task/condition-specific EEG. This work attempts to model biometric signatures independent of task/condition by normalizing the associated variance. Toward this goal, the paper extends ideas from subspace-based text-independent speaker recognition and proposes novel modifications for modeling multi-channel EEG data. The proposed techniques assume that biometric information is present in the entire EEG signal and accumulate statistics across time in a high dimensional space. These high dimensional statistics are then projected to a lower dimensional space where the biometric information is preserved. The lower dimensional embeddings obtained using the proposed approach are shown to be task-independent. The best subspace system identifies individuals with accuracies of 86.4% and 35.9% on datasets with 30 and 920 subjects, respectively, using just nine EEG channels. The paper also provides insights into the subspace model's scalability to unseen tasks and individuals during training and the number of channels needed for subspace modeling.

eess.SP↗

arXiv2021

Front-end Diarization for Percussion Separation in Taniavartanam of Carnatic Music Concerts

Instrument separation in an ensemble is a challenging task. In this work, we address the problem of separating the percussive voices in the taniavartanam segments of Carnatic music. In taniavartanam, a number of percussive instruments play together or in tandem. Separation of instruments in regions where only one percussion is present leads to interference and artifacts at the output, as source separation algorithms assume the presence of multiple percussive voices throughout the audio segment. We prevent this by first subjecting the taniavartanam to diarization. This process results in homogeneous clusters consisting of segments of either a single voice or multiple voices. A cluster of segments with multiple voices is identified using the Gaussian mixture model (GMM), which is then subjected to source separation. A deep recurrent neural network (DRNN) based approach is used to separate the multiple instrument segments. The effectiveness of the proposed system is evaluated on a standard Carnatic music dataset. The proposed approach provides close-to-oracle performance for non-overlapping segments and a significant improvement over traditional separation schemes.

eess.AS↗

arXiv2021

End-to-End Neural Systems for Automatic Children Speech Recognition: An Empirical Study

A key desiderata for inclusive and accessible speech recognition technology is ensuring its robust performance to children's speech. Notably, this includes the rapidly advancing neural network based end-to-end speech recognition systems. Children speech recognition is more challenging due to the larger intra-inter speaker variability in terms of acoustic and linguistic characteristics compared to adult speech. Furthermore, the lack of adequate and appropriate children speech resources adds to the challenge of designing robust end-to-end neural architectures. This study provides a critical assessment of automatic children speech recognition through an empirical study of contemporary state-of-the-art end-to-end speech recognition systems. Insights are provided on the aspects of training data requirements, adaptation on children data, and the effect of children age, utterance lengths, different architectures and loss functions for end-to-end systems and role of language models on the speech recognition performance.

eess.AS↗

arXiv2021

Confusion2vec 2.0: Enriching Ambiguous Spoken Language Representations with Subwords

Word vector representations enable machines to encode human language for spoken language understanding and processing. Confusion2vec, motivated from human speech production and perception, is a word vector representation which encodes ambiguities present in human spoken language in addition to semantics and syntactic information. Confusion2vec provides a robust spoken language representation by considering inherent human language ambiguities. In this paper, we propose a novel word vector space estimation by unsupervised learning on lattices output by an automatic speech recognition (ASR) system. We encode each word in confusion2vec vector space by its constituent subword character n-grams. We show the subword encoding helps better represent the acoustic perceptual ambiguities in human spoken language via information modeled on lattice structured ASR output. The usefulness of the proposed Confusion2vec representation is evaluated using semantic, syntactic and acoustic analogy and word similarity tasks. We also show the benefits of subword modeling for acoustic ambiguity representation on the task of spoken language intent detection. The results significantly outperform existing word vector representations when evaluated on erroneous ASR outputs. We demonstrate that Confusion2vec subword modeling eliminates the need for retraining/adapting the natural language understanding models on ASR transcripts.

cs.CL↗

arXiv2020

TILES-2018, a longitudinal physiologic and behavioral data set of hospital workers

We present a novel longitudinal multimodal corpus of physiological and behavioral data collected from direct clinical providers in a hospital workplace. We designed the study to investigate the use of off-the-shelf wearable and environmental sensors to understand individual-specific constructs such as job performance, interpersonal interaction, and well-being of hospital workers over time in their natural day-to-day job settings. We collected behavioral and physiological data from $n = 212$ participants through Internet-of-Things Bluetooth data hubs, wearable sensors (including a wristband, a biometrics-tracking garment, a smartphone, and an audio-feature recorder), together with a battery of surveys to assess personality traits, behavioral states, job performance, and well-being over time. Besides the default use of the data set, we envision several novel research opportunities and potential applications, including multi-modal and multi-task behavioral modeling, authentication through biometrics, and privacy-aware and privacy-preserving machine learning.

eess.SP↗

arXiv2020

RNN based Incremental Online Spoken Language Understanding

Spoken Language Understanding (SLU) typically comprises of an automatic speech recognition (ASR) followed by a natural language understanding (NLU) module. The two modules process signals in a blocking sequential fashion, i.e., the NLU often has to wait for the ASR to finish processing on an utterance basis, potentially leading to high latencies that render the spoken interaction less natural. In this paper, we propose recurrent neural network (RNN) based incremental processing towards the SLU task of intent detection. The proposed methodology offers lower latencies than a typical SLU system, without any significant reduction in system accuracy. We introduce and analyze different recurrent neural network architectures for incremental and online processing of the ASR transcripts and compare it to the existing offline systems. A lexical End-of-Sentence (EOS) detector is proposed for segmenting the stream of transcript into sentences for intent classification. Intent detection experiments are conducted on benchmark ATIS, Snips and Facebook's multilingual task oriented dialog datasets modified to emulate a continuous incremental stream of words with no utterance demarcation. We also analyze the prospects of early intent detection, before EOS, with our proposed system.

cs.CL↗

arXiv2020

Multi-Scale Speaker Diarization With Neural Affinity Score Fusion

Identifying the identity of the speaker of short segments in human dialogue has been considered one of the most challenging problems in speech signal processing. Speaker representations of short speech segments tend to be unreliable, resulting in poor fidelity of speaker representations in tasks requiring speaker recognition. In this paper, we propose an unconventional method that tackles the trade-off between temporal resolution and the quality of the speaker representations. To find a set of weights that balance the scores from multiple temporal scales of segments, a neural affinity score fusion model is presented. Using the CALLHOME dataset, we show that our proposed multi-scale segmentation and integration approach can achieve a state-of-the-art diarization performance.

eess.AS↗

arXiv2020

Adversarial defense for deep speaker recognition using hybrid adversarial training

Deep neural network based speaker recognition systems can easily be deceived by an adversary using minuscule imperceptible perturbations to the input speech samples. These adversarial attacks pose serious security threats to the speaker recognition systems that use speech biometric. To address this concern, in this work, we propose a new defense mechanism based on a hybrid adversarial training (HAT) setup. In contrast to existing works on countermeasures against adversarial attacks in deep speaker recognition that only use class-boundary information by supervised cross-entropy (CE) loss, we propose to exploit additional information from supervised and unsupervised cues to craft diverse and stronger perturbations for adversarial training. Specifically, we employ multi-task objectives using CE, feature-scattering (FS), and margin losses to create adversarial perturbations and include them for adversarial training to enhance the robustness of the model. We conduct speaker recognition experiments on the Librispeech dataset, and compare the performance with state-of-the-art projected gradient descent (PGD)-based adversarial training which employs only CE objective. The proposed HAT improves adversarial accuracy by absolute 3.29% and 3.18% for PGD and Carlini-Wagner (CW) attacks respectively, while retaining high accuracy on benign examples.

eess.AS↗

arXiv2020

Feature Fusion Strategies for End-to-End Evaluation of Cognitive Behavior Therapy Sessions

Cognitive Behavioral Therapy (CBT) is a goal-oriented psychotherapy for mental health concerns implemented in a conversational setting with broad empirical support for its effectiveness across a range of presenting problems and client populations. The quality of a CBT session is typically assessed by trained human raters who manually assign pre-defined session-level behavioral codes. In this paper, we develop an end-to-end pipeline that converts speech audio to diarized and transcribed text and extracts linguistic features to code the CBT sessions automatically. We investigate both word-level and utterance-level features and propose feature fusion strategies to combine them. The utterance level features include dialog act tags as well as behavioral codes drawn from another well-known talk psychotherapy called Motivational Interviewing (MI). We propose a novel method to augment the word-based features with the utterance level tags for subsequent CBT code estimation. Experiments show that our new fusion strategy outperforms all the studied features, both when used individually and when fused by direct concatenation. We also find that incorporating a sentence segmentation module can further improve the overall system given the preponderance of multi-utterance conversational turns in CBT sessions.

eess.AS↗

arXiv2020

Victim or Perpetrator? Analysis of Violent Characters Portrayals from Movie Scripts

Violent content in the media can influence viewers' perception of the society. For example, frequent depictions of certain demographics as victims or perpetrators of violence can shape stereotyped attitudes. We propose that computational methods can aid in the large-scale analysis of violence in movies. The method we develop characterizes aspects of violent content solely from the language used in the scripts. Thus, our method is applicable to a movie in the earlier stages of content creation even before it is produced. This is complementary to previous works which rely on audio or video post production. In this work, we identify stereotypes in character roles (i.e., victim, perpetrator and narrator) based on the demographics of the actor casted for that role. Our results highlight two significant differences in the frequency of portrayals as well as the demographics of the interaction between victims and perpetrators : (1) female characters appear more often as victims, and (2) perpetrators are more likely to be White if the victim is Black or Latino. To date, we are the first to show that language used in movie scripts is a strong indicator of violent content, and that there are systematic portrayals of certain demographics as victims and perpetrators in a large dataset. This offers novel computational tools to assist in creating awareness of representations in storytelling

cs.CL↗

arXiv2020

An analysis of observation length requirements for machine understanding of human behaviors from spoken language

The task of quantifying human behavior by observing interaction cues is an important and useful one across a range of domains in psychological research and practice. Machine learning-based approaches typically perform this task by first estimating behavior based on cues within an observation window, such as a fixed number of words, and then aggregating the behavior over all the windows in that interaction. The length of this window directly impacts the accuracy of estimation by controlling the amount of information being used. The exact link between window length and accuracy, however, has not been well studied, especially in spoken language. In this paper, we investigate this link and present an analysis framework that determines appropriate window lengths for the task of behavior estimation. Our proposed framework utilizes a two-pronged evaluation approach: (a) extrinsic similarity between machine predictions and human expert annotations, and (b) intrinsic consistency between intra-machine and intra-human behavior relations. We apply our analysis to real-life conversations that are annotated for a large and diverse set of behavior codes and examine the relation between the nature of a behavior and how long it should be observed. We find that behaviors describing negative and positive affect can be accurately estimated from short to medium-length expressions whereas behaviors related to problem-solving and dysphoria require much longer observations and are difficult to quantify from language alone. These findings are found to be generally consistent across different behavior modeling approaches.

cs.CL↗

arXiv2020

Adversarial Attack and Defense Strategies for Deep Speaker Recognition Systems

Robust speaker recognition, including in the presence of malicious attacks, is becoming increasingly important and essential, especially due to the proliferation of several smart speakers and personal agents that interact with an individual's voice commands to perform diverse, and even sensitive tasks. Adversarial attack is a recently revived domain which is shown to be effective in breaking deep neural network-based classifiers, specifically, by forcing them to change their posterior distribution by only perturbing the input samples by a very small amount. Although, significant progress in this realm has been made in the computer vision domain, advances within speaker recognition is still limited. The present expository paper considers several state-of-the-art adversarial attacks to a deep speaker recognition system, employing strong defense methods as countermeasures, and reporting on several ablation studies to obtain a comprehensive understanding of the problem. The experiments show that the speaker recognition systems are vulnerable to adversarial attacks, and the strongest attacks can reduce the accuracy of the system from 94% to even 0%. The study also compares the performances of the employed defense methods in detail, and finds adversarial training based on Projected Gradient Descent (PGD) to be the best defense method in our setting. We hope that the experiments presented in this paper provide baselines that can be useful for the research community interested in further studying adversarial robustness of speaker recognition systems.

eess.AS↗

arXiv2020

Having a Bad Day? Detecting the Impact of Atypical Life Events Using Wearable Sensors

Life events can dramatically affect our psychological state and work performance. Stress, for example, has been linked to professional dissatisfaction, increased anxiety, and workplace burnout. We explore the impact of positive and negative life events on a number of psychological constructs through a multi-month longitudinal study of hospital and aerospace workers. Through causal inference, we demonstrate that positive life events increase positive affect, while negative events increase stress, anxiety and negative affect. While most events have a transient effect on psychological states, major negative events, like illness or attending a funeral, can reduce positive affect for multiple days. Next, we assess whether these events can be detected through wearable sensors, which can cheaply and unobtrusively monitor health-related factors. We show that these sensors paired with embedding-based learning models can be used ``in the wild'' to capture atypical life events in hundreds of workers across both datasets. Overall our results suggest that automated interventions based on physiological sensing may be feasible to help workers regulate the negative effects of life events.

cs.HC↗