相关论文: Align With Purpose: Optimize Desired Properties in…

Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions that may cause performance drops. In this work, we investigate methods for predicting the target domain…

Learning representations unaffected by superficial characteristics is important to ensure that shifts in these characteristics at test time do not compromise downstream prediction performance. For instance, in healthcare applications, we…

Human-computer interaction (HCI) is significantly impacted by delayed responses from a spoken dialogue system. Hence, end-to-end (e2e) spoken language understanding (SLU) solutions have recently been proposed to decrease latency. Such…

Deploying models on target domain data subject to distribution shift requires adaptation. Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available…

Automatic Modulation Classification (AMC) is critical for efficient spectrum management and robust wireless communications. However, AMC remains challenging due to the complex interplay of signal interference and noise. In this work, we…

Unified Speech Recognition (USR) has emerged as a semi-supervised framework for training a single model for audio, visual, and audiovisual speech recognition, achieving state-of-the-art results on in-distribution benchmarks. However, its…

The recent explosion in work on neural topic modeling has been criticized for optimizing automated topic evaluation metrics at the expense of actual meaningful topic identification. But human annotation remains expensive and time-consuming.…

Contextual ASR or hotword customization holds substantial practical value. Despite the impressive performance of current end-to-end (E2E) automatic speech recognition (ASR) systems, they often face challenges in accurately recognizing rare…

We propose a weakly-supervised framework for action labeling in video, where only the order of occurring actions is required during training time. The key challenge is that the per-frame alignments between the input (video) and label…

Siamese networks have shown effective results in unsupervised visual representation learning. These models are designed to learn an invariant representation of two augmentations for one input by maximizing their similarity. In this paper,…

We study the problem of continual test-time adaption where the goal is to adapt a source pre-trained model to a sequence of unlabelled target domains at test time. Existing methods on test-time training suffer from several limitations: (1)…

Multilingual Automatic Speech Recognition (ASR) models have extended the usability of speech technologies to a wide variety of languages. With how many languages these models have to handle, however, a key to understanding their imbalanced…

We report an extension of a Keras Model, called CTCModel, to perform the Connectionist Temporal Classification (CTC) in a transparent way. Combined with Recurrent Neural Networks, the Connectionist Temporal Classification is the reference…

Conformal prediction has been explored as a general and efficient way to provide uncertainty quantification for time series. However, current methods struggle to handle time series data with change points - sudden shifts in the underlying…

Aligning acoustic and linguistic representations is a central challenge to bridge the pre-trained models in knowledge transfer for automatic speech recognition (ASR). This alignment is inherently structured and asymmetric: while multiple…

Connectionist temporal classification (CTC) models are known to have peaky output distributions. Such behavior is not a problem for automatic speech recognition (ASR), but it can cause inaccurate forced alignments (FA), especially at finer…

Recent advancements in text-to-speech (TTS) systems, such as FastSpeech and StyleSpeech, have significantly improved speech generation quality. However, these models often rely on duration generated by external tools like the Montreal…

End-to-end (E2E) systems have shown comparable performance to hybrid systems for automatic speech recognition (ASR). Word timings, as a by-product of ASR, are essential in many applications, especially for subtitling and computer-aided…

Most existing sequence labelling models rely on a fixed decomposition of a target sequence into a sequence of basic units. These methods suffer from two major drawbacks: 1) the set of basic units is fixed, such as the set of words,…

The quality of automatic speech recognition (ASR) is critical to Dialogue Systems as ASR errors propagate to and directly impact downstream tasks such as language understanding (LU). In this paper, we propose multi-task neural approaches to…