Explainable speech quality assessment requires moving beyond Mean Opinion Scores (MOS) to analyze underlying perceptual dimensions. To address this, we introduce a novel post-training method that tailors the foundational Audio Large Language Model for multidimensional reasoning, detection and classification of audio artifacts. First, a calibration stage aligns the model to predict predefined perceptual dimensions. Second, a reinforcement learning stage leverages Group Relative Policy Optimization (GRPO) with dimension-specific rewards to heavily enhance accuracy of descriptions and temporal localization of quality issues. With this approach we reach state-of-the-art results of 0.71 mean PCC score on the multidimensional QualiSpeech benchmark and 13% improvement in MOS prediction driven by RL-based reasoning. Furthermore, our fine-grained GRPO rewards substantially advance the model's ability to pinpoint and classify audio artifacts in time.
Investigating Annotator Bias in Large Language Models for Hate Speech Detection
University of North Alabama（北阿拉巴马大学）；Murray State University（默里州立大学）；Wichita State University（威奇托州立大学）；California State Polytechnic University Pomona（加州州立理工大学波莫纳分校）；Auburn University at Montgomery（奥本大学蒙哥马利分校）；Auburn University（奥本大学）；Gustavus Adolphus College（古斯塔夫斯·阿道弗斯学院）；Stanford University（斯坦福大学）；Amazon GenAI（亚马逊生成式人工智能部门）
Attention has become one of the most commonly used mechanisms in deep learning approaches. The attention mechanism can help the system focus more on the feature space's critical regions. For example, high amplitude regions can play an important role for Speech Emotion Recognition (SER). In this paper, we identify misalignments between the attention and the signal amplitude in the existing multi-head self-attention. To improve the attention area, we propose to use a Focus-Attention (FA) mechanism and a novel Calibration-Attention (CA) mechanism in combination with the multi-head self-attention.…
MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）；Le Mans University（勒芒大学）
Pseudo-label (PL) filtering forms a crucial part of Self-Training (ST) methods for unsupervised domain adaptation. Dropout-based Uncertainty-driven Self-Training (DUST) proceeds by first training a teacher model on source domain labeled data. Then, the teacher model is used to provide PLs for the unlabeled target domain data. Finally, we train a student on augmented labeled and pseudo-labeled data. The process is iterative, where the student becomes the teacher for the next DUST iteration. A crucial step that precedes the student model training in each DUST iteration is filtering out noisy PLs…
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
DeepFake Audio, unlike DeepFake images and videos, has been relatively less explored from detection perspective, and the solutions which exist for the synthetic speech classification either use complex networks or dont generalize to different varieties of synthetic speech obtained using different generative and optimization-based methods. Through this work, we propose a channel-wise recalibration of features using attention feature fusion for synthetic speech detection and compare its performance against different detection methods including End2End models and Resnet-based models on synthetic …
OV-InstructTTS: Towards Open-Vocabulary Instruct Text-to-Speech
The State Key Laboratory of Multimodal Artificial Intelligence Systems（多模态人工智能系统国家重点实验室）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）
Towards Paradigm-General Suicide Risk Detection via Speech LLM
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）；Vanke School of Public Health, Tsinghua University（清华大学万科公共卫生与健康学院）
Quantization-Based Score Calibration for Few-Shot Keyword Spotting with Dynamic Time Warping in Noisy Environments
Department of Electronic Systems, Aalborg University, Denmark（奥尔堡大学电子系统系）；Pioneer Centre for AI, Denmark（丹麦先锋人工智能中心）；Fraunhofer FKIE, Wachtberg, Germany（德国弗劳恩霍夫 FKIE研究所）
