22 accepted papers
Computer-use agents (CUAs) promise to automate complex tasks across operating systems (OS) and the web, but remain vulnerable to indirect prompt injection, where attackers embed malicious content into the environment to hijack agent behavior. Current evaluations of this threat either lack support fo…
Although computer-use agents (CUAs) hold significant potential to automate increasingly complex OS workflows, they can demonstrate unsafe unintended behaviors that deviate from expected outcomes even under benign input contexts. However, exploration of this risk remains largely anecdotal, lacking co…
In this paper, we take a step towards jointly modeling automatic speech recognition (STT) and speech synthesis (TTS) in a fully non-autoregressive way. We develop a novel multimodal framework capable of handling the speech and text modalities as input either individually or together. The proposed mo…
Counter narratives - informed responses to hate speech contexts designed to refute hateful claims and de-escalate encounters - have emerged as an effective hate speech intervention strategy. While previous work has proposed automatic counter narrative generation methods to aid manual interventions,…
In this work, we explore how a real time reading tracker can be built efficiently for children’s voices. While previously proposed reading trackers focused on ASR-based cascaded approaches, we propose a fully end-to-end model making it less prone to lags in voice tracking. We employ a pointer networ…
In recent years, end-to-end approaches have made notable progress in addressing the challenge of speaker diarization, which involves segmenting and identifying speakers in multi-talker recordings. One such approach, Encoder-Decoder Attractors (EDA), has been proposed to handle variable speaker count…
Disfluency detection and classification on children’s speech has a great potential for teaching reading skills. Word-level assessment of children’s speech can help teachers to effectively gauge their students’ progress. Hence, we propose a novel attention-based model to perform word-level disfluency…
RNN Tranducer (RNN-T) technology is very popular for building deployable models for end-to-end (E2E) automatic speech recognition (ASR) and spoken language understanding (SLU). Since these are E2E models operating on speech directly, there remains a potential to improve their performance using purel…
Large language models (LLMs) with in-context learning have demonstrated impressive generalization capabilities in the cross-domain text-to-SQL task, without the use of in-domain annotations. However, incorporating in-domain demonstration examples has been found to greatly enhance LLMs' performance.…
Dialog history plays an important role in spoken language understanding (SLU) performance in a dialog system. For end-to-end (E2E) SLU, previous work has used dialog history in text form, which makes the model dependent on a cascaded automatic speech recognizer (ASR). This rescinds the benefits of a…
Utterance classification performance in low-resource dialogue systems is constrained by an inevitably high degree of data imbalance in class labels. We present a new end-to-end pairwise learning framework that is designed specifically to tackle this phenomenon by inducing a few-shot classification c…
Wet laboratory protocols (WLPs) are critical for conveying reproducible procedures in biological research. They are composed of instructions written in natural language describing the step-wise processing of materials by specific actions. This process flow description for reagents and materials synt…
Embeddings of words and concepts capture syntactic and semantic regularities of language; however, they have seen limited use as tools to study characteristics of different corpora and how they relate to one another. We introduce TextEssence, an interactive system designed to enable comparative anal…
Linguistic analyses in natural language processing (NLP) have often been performed around the static notion of words where the context (surrounding words) is not considered. For example, previous analyses on politeness have focused on comparing the use of static words such as personal pronouns acros…
Simulating the errors made by a speech recognizer on plain text has proven useful to help train downstream NLP tasks to be robust to real ASR errors at test time. Prior work in this domain has focused on modeling confusions at the phonetic level, and using a lexicon to convert from words to phones a…
While deep learning systems have gained significant ground in speech enhancement research, these systems have yet to make use of the full potential of deep learning systems to provide high-level feedback. In particular, phonetic feedback is rare in speech enhancement research even though it includes…
Off-the-shelf speech recognition systems can yield useful results and accelerate application development, but general-purpose systems applied to specialized domains can introduce acoustically small-but semantically catastrophic-errors. Furthermore, sufficient audio data may not be available to devel…
Modeling the errors of a speech recognizer can help simulate errorful recognized speech data from plain text, which has proven useful for tasks like discriminative language modeling, improving robustness of NLP systems, where limited or even no audio data is available at train time. Previous work ty…
In recent years, Residual Networks (ResNets) have significantly increased the modeling power of convolutional neural networks (CNNs) by introducing residual connections. In this paper, we explore the incorporation of spatial and channel attention into the structure of ResNets for noisy speech recogn…
Many state-of-the-art automatic speech recognition (ASR) systems adopt system combination techniques to improve recognition performance. In this paper, we investigate the possibility of transferring knowledge between models for different noisy speech domains and integrating these models via system c…
For the task of speech enhancement, local learning objectives are agnostic to phonetic structures helpful for speech recognition. We propose to add a global criterion to ensure de-noised speech is useful for downstream tasks like ASR. We first train a spectral classifier on clean speech to predict s…
We propose Inference Knowledge Graph, a novel approach of remapping existing, large scale, semantic knowledge graphs into Markov Random Fields in order to create user goal tracking models that could form part of a spoken dialog system. Since semantic knowledge graphs include both entities and their…