相关论文: PIER: A Novel Metric for Evaluating What Matters i…

Dialogue topic segmentation is critical in several dialogue modeling problems. However, popular unsupervised approaches only exploit surface features in assessing topical coherence among utterances. In this work, we address this limitation…

Many automatic speech recognition (ASR) data sets include a single pre-defined test set consisting of one or more speakers whose speech never appears in the training set. This "hold-speaker(s)-out" data partitioning strategy, however, may…

Information Retrieval (IR) systems are designed to deliver relevant content, but traditional systems may not optimize rankings for fairness, neutrality, or the balance of ideas. Consequently, IR can often introduce indexical biases, or…

Recent advances in automatic evaluation metrics for text have shown that deep contextualized word representations, such as those generated by BERT encoders, are helpful for designing metrics that correlate well with human judgements. At the…

Spoof localization, also called segment-level detection, is a crucial task that aims to locate spoofs in partially spoofed audio. The equal error rate (EER) is widely used to measure performance for such biometric scenarios. Although EER is…

Sequence-to-sequence attention-based models on subword units allow simple open-vocabulary end-to-end speech recognition. In this work, we show that such models can achieve competitive results on the Switchboard 300h and LibriSpeech 1000h…

While improvements have been made in automatic speech recognition performance over the last several years, machines continue to have significantly lower performance on accented speech than humans. In addition, the most significant…

It is well-known that speakers who entrain to one another have more successful conversations than those who do not. Previous research has shown that interlocutors entrain on linguistic features in both written and spoken monolingual…

Recognizing code-switched speech is challenging for Automatic Speech Recognition (ASR) for a variety of reasons, including the lack of code-switched training data. Recently, we showed that monolingual ASR systems fine-tuned on code-switched…

In this paper, we provide a theoretical understanding of word embedding and its dimensionality. Motivated by the unitary-invariance of word embedding, we propose the Pairwise Inner Product (PIP) loss, a novel metric on the dissimilarity…

Code-switching, the phenomenon of alternating between two or more languages in a single conversation, presents unique challenges for Natural Language Processing (NLP). Most existing research focuses on either syntactic constraints or neural…

Cross-lingual speech adaptation aims to solve the problem of leveraging multiple rich-resource languages to build models for a low-resource target language. Since the low-resource language has limited training data, speech recognition…

Proportional-integral-derivative (PID) control underlies more than $97\%$ of automated industrial processes. Controlling these processes effectively with respect to some specified set of performance goals requires finding an optimal set of…

Machine Learning (ML) models are trained on in-distribution (ID) data but often encounter out-of-distribution (OOD) inputs during deployment -- posing serious risks in safety-critical domains. Recent works have focused on designing scoring…

Smart word substitution aims to enhance sentence quality by improving word choices; however current benchmarks rely on human-labeled data. Since word choices are inherently subjective, ground-truth word substitutions generated by a small…

Recently, transformer-based generative recommendation has garnered significant attention for user behavior modeling. However, it often requires discretizing items into multi-code representations (e.g., typically four code tokens or more),…

Code-switching (CS) phenomenon occurs when words or phrases from different languages are alternated in a single sentence. Due to data scarcity, building an effective CS Automatic Speech Recognition (ASR) system remains challenging. In this…

Recent information retrieval (IR) models are pre-trained and instruction-tuned on massive datasets and tasks, enabling them to perform well on a wide range of tasks and potentially generalize to unseen tasks with instructions. However,…

Code-switching deals with alternative languages in communication process. Training end-to-end (E2E) automatic speech recognition (ASR) systems for code-switching is especially challenging as code-switching training data are always…

Code-switching (CS) refers to the switching of languages within a speech signal and results in language confusion for automatic speech recognition (ASR). To address language confusion, we propose a language alignment loss (LAL) that aligns…