相关论文: Preference-based training framework for automatic …

Research in modeling subjective metrics for quality assessment has led to the development of no-reference speech models that directly operate on utterance waveforms to predict the Mean Opinion Score (MOS). These models often rely on…

Recent research on speech enhancement (SE) has seen the emergence of deep-learning-based methods. It is still a challenging task to determine the effective ways to increase the generalizability of SE under diverse test conditions. In this…

Automatic subjective speech quality assessment (SSQA) traditionally estimates speech quality on an utterance or system level. While this resolution was adequate for older transmission or synthesis systems that produced speech signals of…

Speech quality in online conferencing applications is typically assessed through human judgements in the form of the mean opinion score (MOS) metric. Since such a labor-intensive approach is not feasible for large-scale speech quality…

Perceptual speech quality is an important performance metric for teleconferencing applications. The mean opinion score (MOS) is standardized for the perceptual evaluation of speech quality and is obtained by asking listeners to rate the…

In this work, we introduce a "score-based assessment" framework for estimating the transferability of pre-trained speech models (PSMs) for fine-tuning target tasks. We leverage upon two representation theories, Bayesian likelihood…

Since the advent of Deep Learning (DL), Speech Enhancement (SE) models have performed well under a variety of noise conditions. However, such systems may still introduce sonic artefacts, sound unnatural, and restrict the ability for a user…

The mean opinion score (MOS) is a standard metric for assessing speech quality, but its singular focus fails to identify specific distortions when low scores are observed. The NISQA dataset addresses this limitation by providing ratings…

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…

Recently, there has been significant interest in replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs), such as Direct Preference Optimization (DPO) and its variants. These…

Direct Preference Optimization (DPO) and its variants have become the de facto standards for aligning large language models (LLMs) with human preferences or specific goals. However, DPO requires high-quality preference data and suffers from…

In the last years decision-focused learning framework, also known as predict-and-optimize, have received increasing attention. In this setting, the predictions of a machine learning model are used as estimated cost coefficients in the…

Contextual biasing improves automatic speech recognition (ASR) by integrating external knowledge, such as user-specific phrases or entities, during decoding. In this work, we use an attention-based biasing decoder to produce scores for…

The Mean Opinion Score (MOS) serves as the standard metric for speech quality assessment, yet biases in human annotations remain underexplored. We conduct the first systematic analysis of gender bias in MOS, revealing that male listeners…

In this article, we provide an experimental observation: Deep neural network (DNN) based speech quality assessment (SQA) models have inherent latent representations where many types of impairments are clustered. While DNN-based SQA models…

Objective speech quality measures are typically used to assess speech enhancement algorithms, but it has been shown that they are sub-optimal as learning objectives because they do not always align well with human subjective ratings. This…

Despite the parallel challenges that audio and text domains face in evaluating generative model outputs, preference learning remains remarkably underexplored in audio applications. Through a PRISMA-guided systematic review of approximately…

We present a preference learning framework for multiple criteria sorting. We consider sorting procedures applying an additive value model with diverse types of marginal value functions (including linear, piecewise-linear, splined, and…

Estimating quality of transmitted speech is known to be a non-trivial task. While traditionally, test participants are asked to rate the quality of samples; nowadays, automated methods are available. These methods can be divided into: 1)…

Speech enhancement(SE) aims to recover clean speech from noisy recordings. Although generative approaches such as score matching and Schrodinger bridge have shown strong effectiveness, they are often computationally expensive. Flow matching…