Related papers: Fast Entropy-Based Methods of Word-Level Confidenc…

Reading comprehension, a fundamental cognitive ability essential for knowledge acquisition, is a complex skill, with a notable number of learners lacking proficiency in this domain. This study introduces innovative tasks for Brain-Computer…

Automated audio captioning models frequently produce overconfident predictions regardless of semantic accuracy, limiting their reliability in deployment. This deficiency stems from two factors: evaluation metrics based on n-gram overlap…

For real-world deployment of automatic speech recognition (ASR), the system is desired to be capable of fast inference while relieving the requirement of computational resources. The recently proposed end-to-end ASR system based on…

Over the last few years, machine learning unlocked previously infeasible features for compression, such as providing guarantees for users' privacy or tailoring compression to specific data statistics (e.g., satellite images or audio…

The majority of research in computational psycholinguistics has concentrated on the processing of words. This study introduces innovative methods for computing sentence-level metrics using multilingual large language models. The metrics…

Contextualized end-to-end automatic speech recognition has been an active research area, with recent efforts focusing on the implicit learning of contextual phrases based on the final loss objective. However, these approaches ignore the…

In the past few years, triplet loss-based metric embeddings have become a de-facto standard for several important computer vision problems, most no-tably, person reidentification. On the other hand, in the area of speech recognition the…

We introduce Entropy2Vec, a novel framework for deriving cross-lingual language representations by leveraging the entropy of monolingual language models. Unlike traditional typological inventories that suffer from feature sparsity and…

Language models (LMs) should provide reliable confidence estimates to help users detect mistakes in their outputs and defer to human experts when necessary. Asking a language model to assess its confidence ("Score your confidence from…

As large language models (LLMs) become increasingly powerful, the sequential nature of autoregressive generation creates a fundamental throughput bottleneck that limits the practical deployment. While Multi-Token Prediction (MTP) has…

Information theoretic quantities play a central role in machine learning. The recent surge in the complexity of data and models has increased the demand for accurate estimation of these quantities. However, as the dimension grows the…

The estimation of entropy rates for stationary discrete-valued stochastic processes is a well studied problem in information theory. However, estimating the entropy rate for stationary continuous-valued stochastic processes has not received…

We show that confidence intervals in a variance component model, with asymptotically correct uniform coverage probability, can be obtained by inverting certain test-statistics based on the score for the restricted likelihood. The results…

Self-supervised speech representations have been shown to be effective in a variety of speech applications. However, existing representation learning methods generally rely on the autoregressive model and/or observed global dependencies…

One of limitations in end-to-end automatic speech recognition (ASR) framework is its performance would be compromised if train-test utterance lengths are mismatched. In this paper, we propose an on-the-fly random utterance concatenation…

As end-to-end automatic speech recognition (ASR) models reach promising performance, various downstream tasks rely on good confidence estimators for these systems. Recent research has shown that model-based confidence estimators have a…

Large language models (LLMs) are increasingly deployed in domains where errors carry high social, scientific, or safety costs. Yet standard confidence estimators, such as token likelihood, semantic similarity and multi-sample consistency,…

Transformer-based end-to-end speech recognition models have received considerable attention in recent years due to their high training speed and ability to model a long-range global context. Position embedding in the transformer…

Automatic recognition systems for child speech are lagging behind those dedicated to adult speech in the race of performance. This phenomenon is due to the high acoustic and linguistic variability present in child speech caused by their…

Speech processing requires very efficient methods and algorithms. Finite-state transducers have been shown recently both to constitute a very useful abstract model and to lead to highly efficient time and space algorithms in this field. We…