Ahmed Tewfik

Yan Han, Gregory Holste, Ying Ding et al.

Before the recent success of deep learning methods for automated medical image analysis, practitioners used handcrafted radiomic features to quantitatively describe local patches of medical images. However, extracting discriminative radiomic features relies on accurate pathology localization, which is difficult to acquire in real-world settings. Despite advances in disease classification and localization from chest X-rays, many approaches fail to incorporate clinically-informed domain knowledge. For these reasons, we propose a Radiomics-Guided Transformer (RGT) that fuses \textit{global} image information with \textit{local} knowledge-guided radiomics information to provide accurate cardiopulmonary pathology localization and classification \textit{without any bounding box annotations}. RGT consists of an image Transformer branch, a radiomics Transformer branch, and fusion layers that aggregate image and radiomic information. Using the learned self-attention of its image branch, RGT extracts a bounding box for which to compute radiomic features, which are further processed by the radiomics branch; learned image and radiomic features are then fused and mutually interact via cross-attention layers. Thus, RGT utilizes a novel end-to-end feedback loop that can bootstrap accurate pathology localization only using image-level disease labels. Experiments on the NIH ChestXRay dataset demonstrate that RGT outperforms prior works in weakly supervised disease localization (by an average margin of 3.6\% over various intersection-over-union thresholds) and classification (by 1.1\% in average area under the receiver operating characteristic curve). We publicly release our codes and pre-trained models at \url{https://github.com/VITA-Group/chext}.

Madhumitha Sakthi, Ahmed Tewfik, Marius Arvinte et al.

Automotive radar has increasingly attracted attention due to growing interest in autonomous driving technologies. Acquiring situational awareness using multimodal data collected at high sampling rates by various sensing devices including cameras, LiDAR, and radar requires considerable power, memory and compute resources which are often limited at an edge device. In this paper, we present a novel adaptive radar sub-sampling algorithm designed to identify regions that require more detailed/accurate reconstruction based on prior environmental conditions' knowledge, enabling near-optimal performance at considerably lower effective sampling rates. Designed to robustly perform under variable weather conditions, the algorithm was shown on the Oxford raw radar and RADIATE dataset to achieve accurate reconstruction utilizing only 10% of the original samples in good weather and 20% in extreme (snow, fog) weather conditions. A further modification of the algorithm incorporates object motion to enable reliable identification of important regions. This includes monitoring possible future occlusions caused by objects detected in the present frame. Finally, we train a YOLO network on the RADIATE dataset to perform object detection directly on RADAR data and obtain a 6.6% AP50 improvement over the baseline Faster R-CNN network.

Pranay Dighe, Prateeth Nayak, Oggi Rudovic et al.

Accurate prediction of the user intent to interact with a voice assistant (VA) on a device (e.g. on the phone) is critical for achieving naturalistic, engaging, and privacy-centric interactions with the VA. To this end, we present a novel approach to predict the user's intent (the user speaking to the device or not) directly from acoustic and textual information encoded at subword tokens which are obtained via an end-to-end ASR model. Modeling directly the subword tokens, compared to modeling of the phonemes and/or full words, has at least two advantages: (i) it provides a unique vocabulary representation, where each token has a semantic meaning, in contrast to the phoneme-level representations, (ii) each subword token has a reusable "sub"-word acoustic pattern (that can be used to construct multiple full words), resulting in a largely reduced vocabulary space than of the full words. To learn the subword representations for the audio-to-intent classification, we extract: (i) acoustic information from an E2E-ASR model, which provides frame-level CTC posterior probabilities for the subword tokens, and (ii) textual information from a pre-trained continuous bag-of-words model capturing the semantic meaning of the subword tokens. The key to our approach is the way it combines acoustic subword-level posteriors with text information using the notion of positional-encoding in order to account for multiple ASR hypotheses simultaneously. We show that our approach provides more robust and richer representations for audio-to-intent classification, and is highly accurate with correctly mitigating 93.3% of unintended user audio from invoking the smart assistant at 99% true positive rate.

Madhumitha Sakthi, Ahmed Tewfik, Marius Arvinte et al.

Robust and accurate sensing is of critical importance for advancing autonomous automotive systems. The need to acquire situational awareness in complex urban conditions using sensors such as radar has motivated research on power and latency-efficient signal acquisition methods. In this paper, we present an end-to-end signal processing pipeline, capable of operating in extreme weather conditions, that relies on sub-sampled radar data to perform object detection in vehicular settings. The results of the object detection are further utilized to sub-sample forthcoming radar data, which stands in contrast to prior work where the sub-sampling relies on image information. We show robust detection based on radar data reconstructed using 20% of samples under extreme weather conditions such as snow or fog, and on low-illuminated nights. Additionally, we generate 20% sampled radar data in a fine-tuning set and show 1.1% gain in AP50 across scenes and 3% AP50 gain in motorway condition.

Pranay Dighe, Yi Su, Shangshang Zheng et al.

While large language models excel in a variety of natural language processing (NLP) tasks, to perform well on spoken language understanding (SLU) tasks, they must either rely on off-the-shelf automatic speech recognition (ASR) systems for transcription, or be equipped with an in-built speech modality. This work focuses on the former scenario, where LLM's accuracy on SLU tasks is constrained by the accuracy of a fixed ASR system on the spoken input. Specifically, we tackle speech-intent classification task, where a high word-error-rate can limit the LLM's ability to understand the spoken intent. Instead of chasing a high accuracy by designing complex or specialized architectures regardless of deployment costs, we seek to answer how far we can go without substantially changing the underlying ASR and LLM, which can potentially be shared by multiple unrelated tasks. To this end, we propose prompting the LLM with an n-best list of ASR hypotheses instead of only the error-prone 1-best hypothesis. We explore prompt-engineering to explain the concept of n-best lists to the LLM; followed by the finetuning of Low-Rank Adapters on the downstream tasks. Our approach using n-best lists proves to be effective on a device-directed speech detection task as well as on a keyword spotting task, where systems using n-best list prompts outperform those using 1-best ASR hypothesis; thus paving the way for an efficient method to exploit ASR uncertainty via LLMs for speech-based applications.

Prateeth Nayak, Takuya Higuchi, Anmol Gupta et al.

Voice trigger detection is an important task, which enables activating a voice assistant when a target user speaks a keyword phrase. A detector is typically trained on speech data independent of speaker information and used for the voice trigger detection task. However, such a speaker independent voice trigger detector typically suffers from performance degradation on speech from underrepresented groups, such as accented speakers. In this work, we propose a novel voice trigger detector that can use a small number of utterances from a target speaker to improve detection accuracy. Our proposed model employs an encoder-decoder architecture. While the encoder performs speaker independent voice trigger detection, similar to the conventional detector, the decoder predicts a personalized embedding for each utterance. A personalized voice trigger score is then obtained as a similarity score between the embeddings of enrollment utterances and a test utterance. The personalized embedding allows adapting to target speaker's speech when computing the voice trigger score, hence improving voice trigger detection accuracy. Experimental results show that the proposed approach achieves a 38% relative reduction in a false rejection rate (FRR) compared to a baseline speaker independent voice trigger model.

Utkarsh Oggy Sarawgi, John Berkowitz, Vineet Garg et al.

Streaming neural network models for fast frame-wise responses to various speech and sensory signals are widely adopted on resource-constrained platforms. Hence, increasing the learning capacity of such streaming models (i.e., by adding more parameters) to improve the predictive power may not be viable for real-world tasks. In this work, we propose a new loss, Streaming Anchor Loss (SAL), to better utilize the given learning capacity by encouraging the model to learn more from essential frames. More specifically, our SAL and its focal variations dynamically modulate the frame-wise cross entropy loss based on the importance of the corresponding frames so that a higher loss penalty is assigned for frames within the temporal proximity of semantically critical events. Therefore, our loss ensures that the model training focuses on predicting the relatively rare but task-relevant frames. Experimental results with standard lightweight convolutional and recurrent streaming networks on three different speech based detection tasks demonstrate that SAL enables the model to learn the overall task more effectively with improved accuracy and latency, without any additional data, model parameters, or architectural changes.

Yan Han, Chongyan Chen, Liyan Tang et al.

Chest X-ray becomes one of the most common medical diagnoses due to its noninvasiveness. The number of chest X-ray images has skyrocketed, but reading chest X-rays still have been manually performed by radiologists, which creates huge burnouts and delays. Traditionally, radiomics, as a subfield of radiology that can extract a large number of quantitative features from medical images, demonstrates its potential to facilitate medical imaging diagnosis before the deep learning era. In this paper, we develop an end-to-end framework, ChexRadiNet, that can utilize the radiomics features to improve the abnormality classification performance. Specifically, ChexRadiNet first applies a light-weight but efficient triplet-attention mechanism to classify the chest X-rays and highlight the abnormal regions. Then it uses the generated class activation map to extract radiomic features, which further guides our model to learn more robust image features. After a number of iterations and with the help of radiomic features, our framework can converge to more accurate image regions. We evaluate the ChexRadiNet framework using three public datasets: NIH ChestX-ray, CheXpert, and MIMIC-CXR. We find that ChexRadiNet outperforms the state-of-the-art on both disease detection (0.843 in AUC) and localization (0.679 in T(IoU) = 0.1). We will make the code publicly available at https://github.com/bionlplab/lung_disease_detection_amia2021, with the hope that this method can facilitate the development of automatic systems with a higher-level understanding of the radiological world.

Ognjen, Rudovic, Pranay Dighe et al.

Follow-up conversations with virtual assistants (VAs) enable a user to seamlessly interact with a VA without the need to repeatedly invoke it using a keyword (after the first query). Therefore, accurate Device-directed Speech Detection (DDSD) from the follow-up queries is critical for enabling naturalistic user experience. To this end, we explore the notion of Large Language Models (LLMs) and model the first query when making inference about the follow-ups (based on the ASR-decoded text), via prompting of a pretrained LLM, or by adapting a binary classifier on top of the LLM. In doing so, we also exploit the ASR uncertainty when designing the LLM prompts. We show on the real-world dataset of follow-up conversations that this approach yields large gains (20-40% reduction in false alarms at 10% fixed false rejects) due to the joint modeling of the previous speech context and ASR uncertainty, compared to when follow-ups are modeled alone.

Shruti Palaskar, Oggi Rudovic, Sameer Dharur et al.

Although Large Language Models (LLMs) have shown promise for human-like conversations, they are primarily pre-trained on text data. Incorporating audio or video improves performance, but collecting large-scale multimodal data and pre-training multimodal LLMs is challenging. To this end, we propose a Fusion Low Rank Adaptation (FLoRA) technique that efficiently adapts a pre-trained unimodal LLM to consume new, previously unseen modalities via low rank adaptation. For device-directed speech detection, using FLoRA, the multimodal LLM achieves 22% relative reduction in equal error rate (EER) over the text-only approach and attains performance parity with its full fine-tuning (FFT) counterpart while needing to tune only a fraction of its parameters. Furthermore, with the newly introduced adapter dropout, FLoRA is robust to missing data, improving over FFT by 20% lower EER and 56% lower false accept rate. The proposed approach scales well for model sizes from 16M to 3B parameters.

Vineet Garg, Ognjen Rudovic, Pranay Dighe et al.

We address the problem of detecting speech directed to a device that does not contain a specific wake-word. Specifically, we focus on audio coming from a touch-based invocation. Mitigating virtual assistants (VAs) activation due to accidental button presses is critical for user experience. While the majority of approaches to false trigger mitigation (FTM) are designed to detect the presence of a target keyword, inferring user intent in absence of keyword is difficult. This also poses a challenge when creating the training/evaluation data for such systems due to inherent ambiguity in the user's data. To this end, we propose a novel FTM approach that uses weakly-labeled training data obtained with a newly introduced data sampling strategy. While this sampling strategy reduces data annotation efforts, the data labels are noisy as the data are not annotated manually. We use these data to train an acoustics-only model for the FTM task by regularizing its loss function via knowledge distillation from an ASR-based (LatticeRNN) model. This improves the model decisions, resulting in 66% gain in accuracy, as measured by equal-error-rate (EER), over the base acoustics-only model. We also show that the ensemble of the LatticeRNN and acoustic-distilled models brings further accuracy improvement of 20%.

Yan Han, Chongyan Chen, Ahmed Tewfik et al.

Building a highly accurate predictive model for classification and localization of abnormalities in chest X-rays usually requires a large number of manually annotated labels and pixel regions (bounding boxes) of abnormalities. However, it is expensive to acquire such annotations, especially the bounding boxes. Recently, contrastive learning has shown strong promise in leveraging unlabeled natural images to produce highly generalizable and discriminative features. However, extending its power to the medical image domain is under-explored and highly non-trivial, since medical images are much less amendable to data augmentations. In contrast, their prior knowledge, as well as radiomic features, is often crucial. To bridge this gap, we propose an end-to-end semi-supervised knowledge-augmented contrastive learning framework, that simultaneously performs disease classification and localization tasks. The key knob of our framework is a unique positive sampling approach tailored for the medical images, by seamlessly integrating radiomic features as a knowledge augmentation. Specifically, we first apply an image encoder to classify the chest X-rays and to generate the image features. We next leverage Grad-CAM to highlight the crucial (abnormal) regions for chest X-rays (even when unannotated), from which we extract radiomic features. The radiomic features are then passed through another dedicated encoder to act as the positive sample for the image features generated from the same chest X-ray. In this way, our framework constitutes a feedback loop for image and radiomic modality features to mutually reinforce each other. Their contrasting yields knowledge-augmented representations that are both robust and interpretable. Extensive experiments on the NIH Chest X-ray dataset demonstrate that our approach outperforms existing baselines in both classification and localization tasks.

Madhumitha Sakthi, Ahmed Tewfik

The growing urban complexity demands an efficient algorithm to acquire and process various sensor information from autonomous vehicles. In this paper, we introduce an algorithm to utilize object detection results from the image to adaptively sample and acquire radar data using Compressed Sensing (CS). This novel algorithm is motivated by the hypothesis that with a limited sampling budget, allocating more sampling budget to areas with the object as opposed to a uniform sampling ultimately improves relevant object detection performance. We improve detection performance by dynamically allocating a lower sampling rate to objects such as buses than pedestrians leading to better reconstruction than baseline across areas with objects of interest. We automate the sampling rate allocation using linear programming and show significant time savings while reducing the radar block size by a factor of 2. We also analyze a Binary Permuted Diagonal measurement matrix for radar acquisition which is hardware-efficient and show its performance is similar to Gaussian and Binary Permuted Block Diagonal matrix. Our experiments on the Oxford radar dataset show an effective reconstruction of objects of interest with 10% sampling rate. Finally, we develop a transformer-based 2D object detection network using the NuScenes radar and image data.

Gautam Krishna, Co Tran, Mason Carnahan et al.

In this paper we introduce a recurrent neural network (RNN) based variational autoencoder (VAE) model with a new constrained loss function that can generate more meaningful electroencephalography (EEG) features from raw EEG features to improve the performance of EEG based speech recognition systems. We demonstrate that both continuous and isolated speech recognition systems trained and tested using EEG features generated from raw EEG features using our VAE model results in improved performance and we demonstrate our results for a limited English vocabulary consisting of 30 unique sentences for continuous speech recognition and for an English vocabulary consisting of 2 unique sentences for isolated speech recognition. We compare our method with another recently introduced method described by authors in [1] to improve the performance of EEG based continuous speech recognition systems and we demonstrate that our method outperforms their method as vocabulary size increases when trained and tested using the same data set. Even though we demonstrate results only for automatic speech recognition (ASR) experiments in this paper, the proposed VAE model with constrained loss function can be extended to a variety of other EEG based brain computer interface (BCI) applications.

Gautam Krishna, Co Tran, Mason Carnahan et al.

In this paper we demonstrate that it is possible to generate more meaningful electroencephalography (EEG) features from raw EEG features using generative adversarial networks (GAN) to improve the performance of EEG based continuous speech recognition systems. We improve the results demonstrated by authors in [1] using their data sets for for some of the test time experiments and for other cases our results were comparable with theirs. Our proposed approach can be implemented without using any additional sensor information, whereas in [1] authors used additional features like acoustic or articulatory information to improve the performance of EEG based continuous speech recognition systems.

Gautam Krishna, Co Tran, Mason Carnahan et al.

The electroencephalography (EEG) signals recorded in parallel with speech are used to perform isolated and continuous speech recognition. During speaking process, one also hears his or her own speech and this speech perception is also reflected in the recorded EEG signals. In this paper we investigate whether it is possible to separate out this speech perception component from EEG signals in order to design more robust EEG based speech recognition systems. We further demonstrate predicting EEG signals recorded in parallel with speaking from EEG signals recorded in parallel with passive listening and vice versa with very low normalized root mean squared error (RMSE). We finally demonstrate both isolated and continuous speech recognition using EEG signals recorded in parallel with listening, speaking and improve the previous connectionist temporal classification (CTC) model results demonstrated by authors in [1] using their data set.

Gautam Krishna, Co Tran, Mason Carnahan et al.

In [1,2] authors provided preliminary results for synthesizing speech from electroencephalography (EEG) features where they first predict acoustic features from EEG features and then the speech is reconstructed from the predicted acoustic features using griffin lim reconstruction algorithm. In this paper we first introduce a deep learning model that takes raw EEG waveform signals as input and directly produces audio waveform as output. We then demonstrate predicting 16 different acoustic features from EEG features. We demonstrate our results for both spoken and listen condition in this paper. The results presented in this paper shows how different acoustic features are related to non-invasive neural EEG signals recorded during speech perception and production.

Gautam Krishna, Co Tran, Mason Carnahan et al.

In this paper we explore predicting facial or lip video features from electroencephalography (EEG) features and predicting EEG features from recorded facial or lip video frames using deep learning models. The subjects were asked to read out loud English sentences shown to them on a computer screen and their simultaneous EEG signals and facial video frames were recorded. Our model was able to generate very broad characteristics of the facial or lip video frame from input EEG features. Our results demonstrate the first step towards synthesizing high quality facial or lip video from recorded EEG features. We demonstrate results for a data set consisting of seven subjects.

Gautam Krishna, Co Tran, Mason Carnahan et al.

In this paper we introduce attention-regression model to demonstrate predicting acoustic features from electroencephalography (EEG) features recorded in parallel with spoken sentences. First we demonstrate predicting acoustic features directly from EEG features using our attention model and then we demonstrate predicting acoustic features from EEG features using a two-step approach where in the first step we use our attention model to predict articulatory features from EEG features and then in second step another attention-regression model is trained to transform the predicted articulatory features to acoustic features. Our proposed attention-regression model demonstrates superior performance compared to the regression model introduced by authors in [1] when tested using their data set for majority of the subjects during test time. The results presented in this paper further advances the work described by authors in [1].

Gautam Krishna, Co Tran, Mason Carnahan et al.

In this paper we explore speaker identification using electroencephalography (EEG) signals. The performance of speaker identification systems degrades in presence of background noise, this paper demonstrates that EEG features can be used to enhance the performance of speaker identification systems operating in presence and absence of background noise. The paper further demonstrates that in presence of high background noise, speaker identification system using only EEG features as input demonstrates better performance than the system using only acoustic features as input.

Marius Arvinte, Ahmed Tewfik, Sriram Vishwanath

We introduce an adversarial sample detection algorithm based on image residuals, specifically designed to guard against patch-based attacks. The image residual is obtained as the difference between an input image and a denoised version of it, and a discriminator is trained to distinguish between clean and adversarial samples. More precisely, we use a wavelet domain algorithm for denoising images and demonstrate that the obtained residuals act as a digital fingerprint for adversarial attacks. To emulate the limitations of a physical adversary, we evaluate the performance of our approach against localized (patch-based) adversarial attacks, including in settings where the adversary has complete knowledge about the detection scheme. Our results show that the proposed detection method generalizes to previously unseen, stronger attacks and that it is able to reduce the success rate (conversely, increase the computational effort) of an adaptive attacker.

Gautam Krishna, Co Tran, Mason Carnahan et al.

In this paper we explore continuous silent speech recognition using electroencephalography (EEG) signals. We implemented a connectionist temporal classification (CTC) automatic speech recognition (ASR) model to translate EEG signals recorded in parallel while subjects were reading English sentences in their mind without producing any voice to text. Our results demonstrate the feasibility of using EEG signals for performing continuous silent speech recognition. We demonstrate our results for a limited English vocabulary consisting of 30 unique sentences.