Related papers: Calibrate and Refine! A Novel and Agile Framework …

Error correction in automatic speech recognition (ASR) aims to correct those incorrect words in sentences generated by ASR models. Since recent ASR models usually have low word error rate (WER), to avoid affecting originally correct tokens,…

Robustness has become a critical attribute for the deployment of RAG systems in real-world applications. Existing research focuses on robustness to explicit noise (e.g., document semantics) but overlooks implicit noise (spurious features).…

Intent-based network (IBN) is a promising solution to automate network operation and management. IBN aims to offer human-tailored network interaction, allowing the network to communicate in a way that aligns with the network users'…

Recent work has shown that inference-time reasoning and reflection can improve text-to-image generation without retraining. However, existing approaches often rely on implicit, holistic critiques or unconstrained prompt rewrites, making…

The dialogue systems in customer services have been developed with neural models to provide users with precise answers and round-the-clock support in task-oriented conversations by detecting customer intents based on their utterances.…

The robust self-training (RST) framework has emerged as a prominent approach for semi-supervised adversarial training. To explore the possibility of tackling more complicated tasks with even lower labeling budgets, unlike prior approaches…

Multilingual automatic speech recognition (ASR) models have shown great promise in recent years because of the simplified model training and deployment process. Conventional methods either train a universal multilingual model without taking…

Automatic speech recognition (ASR) has been an essential component of computer assisted language learning (CALL) and computer assisted language testing (CALT) for many years. As this technology continues to develop rapidly, it is important…

Recent advancement in deep learning encouraged developing large automatic speech recognition (ASR) models that achieve promising results while ignoring computational and memory constraints. However, deploying such models on low resource…

This work presents our end-to-end (E2E) automatic speech recognition (ASR) model targetting at robust speech recognition, called Integraded speech Recognition with enhanced speech Input for Self-supervised learning representation (IRIS).…

Automatic Speech Recognition (ASR) in professional settings faces challenges that existing benchmarks underplay: dense domain terminology, formal register variation, and near-zero tolerance for critical entity errors. We present…

RNN-T models are widely used in ASR, which rely on the RNN-T loss to achieve length alignment between input audio and target sequence. However, the implementation complexity and the alignment-based optimization target of RNN-T loss lead to…

We propose a novel approach for blind room impulse response (RIR) estimation systems in the context of a downstream application scenario, far-field automatic speech recognition (ASR). We first draw the connection between improved RIR…

Deploying small language models (7-9B parameters) as autonomous agents requires trust in their reasoning, not just their outputs. We reveal a critical reliability crisis: 50-69\% of correct answers from these models contain fundamentally…

Accurately finding the wrong words in the automatic speech recognition (ASR) hypothesis and recovering them well-founded is the goal of speech error correction. In this paper, we propose a non-autoregressive speech error correction method.…

Linguistic anomalies detectable in spontaneous speech have shown promise for various clinical applications including screening for dementia and other forms of cognitive impairment. The feasibility of deploying automated tools that can…

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible. However, emitting fast without degrading quality, as measured by word error rate (WER), is highly challenging. Existing…

The development of deep learning based image representation learning (IRL) methods has attracted great attention for various image understanding problems. Most of these methods require the availability of a high quantity and quality of…

Despite recent advances, Automatic Speech Recognition (ASR) systems are still far from perfect. Typical errors include acronyms, named entities, and domain-specific special words for which little or no labeled data is available. To address…

The deployment of multimodal models in high-stakes domains, such as self-driving vehicles and medical diagnostics, demands not only strong predictive performance but also reliable mechanisms for detecting failures. In this work, we address…