惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Y
Y Combinator Blog
The GitHub Blog
The GitHub Blog
云风的 BLOG
云风的 BLOG
Engineering at Meta
Engineering at Meta
Google DeepMind News
Google DeepMind News
aimingoo的专栏
aimingoo的专栏
Recent Announcements
Recent Announcements
A
About on SuperTechFans
U
Unit 42
MyScale Blog
MyScale Blog
J
Java Code Geeks
博客园_首页
Blog — PlanetScale
Blog — PlanetScale
D
Docker
Microsoft Azure Blog
Microsoft Azure Blog
博客园 - 司徒正美
量子位
月光博客
月光博客
G
Google Developers Blog
V
V2EX
博客园 - 聂微东
宝玉的分享
宝玉的分享
IT之家
IT之家
Vercel News
Vercel News

eess.AS updates on arXiv.org

Dependence on Early and Late Reverberation of Single-Channel Speaker Distance Estimation MIST: Multimodal Interactive Speech-based Tool-calling Conversational Assistants for Smart Homes LiVeAction: a Lightweight, Versatile, and Asymmetric Neural Codec Design for Real-time Operation Weight-Decay Turns Transformer Loss Landscapes Villani: Functional-Analytic Foundations for Optimization and Generalization PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling Predictive-Generative Drift Decomposition for Speech Enhancement and Separation Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning JASTIN: Aligning LLMs for Zero-Shot Audio and Speech Evaluation via Natural Language Instructions Phoneme-Level Deepfake Detection Across Emotional Conditions Using Self-Supervised Embeddings When Audio-Language Models Fail to Leverage Multimodal Context for Dysarthric Speech Recognition Dimensionality-Aware Anomaly Detection in Learned Representations of Self-Supervised Speech Models Mitigating Multimodal LLMs Hallucinations via Relevance Propagation at Inference Time Virtual Speech Therapist: A Clinician-in-the-Loop AI Speech Therapy Agent for Personalized and Supervised Therapy LASE: Language-Adversarial Speaker Encoding for Indic Cross-Script Identity Preservation Towards Improving Speaker Distance Estimation through Generative Impulse Response Augmentation Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe MMAudioReverbs: Video-Guided Acoustic Modeling for Dereverberation and Room Impulse Response Estimation Alethia: A Foundational Encoder for Voice Deepfakes From Birdsong to Rumbles: Classifying Elephant Calls with Out-of-Species Embeddings Beyond the Baseband: Adaptive Multi-Band Encoding for Full-Spectrum Bioacoustics Classification Predicting Upcoming Stuttering Events from Three-Second Audio: Stratified Evaluation Reveals Severity-Selective Precursors, and the Model Deploys Fully On-Device The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation DiffAnon: Diffusion-based Prosody Control for Voice Anonymization Recurrence-Based Nonlinear Vocal Dynamics as Digital Biomarkers for Depression Detection from Conversational Speech One Voice, Many Tongues: Cross-Lingual Voice Cloning for Scientific Speech Similarity Choice and Negative Scaling in Supervised Contrastive Learning for Deepfake Audio Detection Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models Praxy Voice: Voice-Prompt Recovery + BUPS for Commercial-Class Indic TTS from a Frozen Non-Indic Base at Zero Commercial-Training-Data Cost
Irrelevant speech effect in open plan offices: A laborato...
2019-03-04 · via eess.AS updates on arXiv.org

It seems now accepted that speech noise in open plan offices is the main source of discomfort for employees. This work follows a series of studies conducted at INRS France and INSA Lyon based on Hongisto's theoretical model (2005) linking the Decrease in Performance (DP) and the Speech Transmission Index (STI). This model predicts that for STI values between 0.7 and 1, which means a speech signal close to 100% of intelligibility, the DP remains constant at about 7%. The experiment that we carried out aimed to gather more information about the relation between DP and STI, varying the STI value up to 0.9. Fifty-five subjects between 25-59 years old participated in the experiment. First, some psychological parameters were observed in order to better characterize the inter-subjects variability. Then, subjects performed a Working-Memory (WM) task in silence and in four different sound conditions (STI from 0.25 to 0.9). This task was customized by an initial measure of mnemonic span so that two different cognitive loads (low/high) were equally defined for each subject around their span value. Subjects also subjectively evaluated their mental load and discomfort at the end of each WM task, for each noise condition. Results show a significant effect of the STI on the DP, the mental load and the discomfort. Furthermore, a significant correlation was found between the age of subjects and their performance during the WM task. This result was confirmed by a cluster analysis that enabled us to separate the subjects on two different groups, one group of younger and more efficient subjects and one group of older and less efficient subjects. General results did not show any increase of DP for the highest STI values, so the "plateau" hypothesis of Hongisto's model cannot be rejected on the basis of this experiment.