相关论文: Universal Preference-Score-based Pairwise Speech Q…

The quality of the speech communication systems, which include noise suppression algorithms, are typically evaluated in laboratory experiments according to the ITU-T Rec. P.835, in which participants rate background noise, speech signal,…

Curating datasets that span multiple languages is challenging. To make the collection more scalable, researchers often incorporate one or more imperfect classifiers in the process, like language identification models. These models, however,…

In a subjective experiment to evaluate the perceptual audiovisual quality of multimedia and television services, raw opinion scores collected from test subjects are often noisy and unreliable. To produce the final mean opinion scores (MOS),…

Mean Opinion Score (MOS) is a popular measure for evaluating synthesized speech. However, the scores obtained in MOS tests are heavily dependent upon many contextual factors. One such factor is the overall range of quality of the samples…

Noisy self-reported empathy scores challenge supervised learning for empathy regression. While many algorithms have been proposed for learning with noisy labels in textual classification problems, the regression counterpart is relatively…

Bias-transforming methods of fairness-aware machine learning aim to correct a non-neutral status quo with respect to a protected attribute (PA). Current methods, however, lack an explicit formulation of what drives non-neutrality. We…

Single-channel deep speech enhancement approaches often estimate a single multiplicative mask to extract clean speech without a measure of its accuracy. Instead, in this work, we propose to quantify the uncertainty associated with clean…

Universal sound separation (USS) is a task to separate arbitrary sounds from an audio mixture. Existing USS systems are capable of separating arbitrary sources, given a few examples of the target sources as queries. However, separating…

Speech enhancement (SE) based on diffusion probabilistic models has exhibited impressive performance, while requiring a relatively high number of function evaluations (NFE). Recently, SE based on flow matching has been proposed, which…

Unsupervised commonsense question answering is appealing since it does not rely on any labeled task data. Among existing work, a popular solution is to use pre-trained language models to score candidate choices directly conditioned on the…

While deep learning has made impressive progress in speech synthesis and voice conversion, the assessment of the synthesized speech is still carried out by human participants. Several recent papers have proposed deep-learning-based…

Existing objective evaluation metrics for voice conversion (VC) are not always correlated with human perception. Therefore, training VC models with such criteria may not effectively improve naturalness and similarity of converted speech. In…

Researches have shown accent classification can be improved by integrating semantic information into pure acoustic approach. In this work, we combine phonetic knowledge, such as vowels, with enhanced acoustic features to build an improved…

Large language models have been widely adopted in natural language processing, yet they face the challenge of generating unreliable content. Recent works aim to reduce misinformation and hallucinations by resorting to attribution as a means…

Conversational Question Answering (ConvQA) involves multiple subtasks, i) to understand incomplete questions in their context, ii) to retrieve relevant information, and iii) to generate answers. This work presents PRAISE, a pipeline-based…

In automated pronunciation assessment, recent emphasis progressively lies on evaluating multiple aspects to provide enriched feedback. However, acquiring multi-aspect-score labeled data for non-native language learners' speech poses…

Recent advances in human preference alignment have significantly improved multimodal generation and understanding. A key approach is to train reward models that provide supervision signals for preference optimization. However, existing…

In this paper, we propose a unified pre-training approach called UniSpeech to learn speech representations with both unlabeled and labeled data, in which supervised phonetic CTC learning and phonetically-aware contrastive self-supervised…

The quality of a multilingual speech recognition system can be improved by adaptation methods if the input language is specified. For systems that can accept multilingual inputs, the popular approach is to apply a language identifier to the…

We propose a scalable Bayesian preference learning method for jointly predicting the preferences of individuals as well as the consensus of a crowd from pairwise labels. Peoples' opinions often differ greatly, making it difficult to predict…