ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

~ similar to 2606.27543· 14 results

cs.LGcs.SDEmpiricalRecentJul 24, 2026

Synthetic Speech, Real Signal: Paralinguistic Preservation and Cross-Lingual Augmentation via Voice Cloning

Roseline Polle, Owen Parsons, George Fairs, Luis Miguel San Martin Fernandez +4 more

Eight voice cloning models are benchmarked on five paralinguistic tasks, showing most preserve signal with modest degradation. Cloning English clinical speech into Japanese outperforms raw cross-lingu…

View →
eess.AScs.SDEmpiricalRecentJul 28, 2026

Multi-Phonation Graph Learning with Self-Supervised Speech Embeddings for ALS Detection and Progression Prediction

Behrad TaghiBeyglou, Fatemeh Bagheri, Ervin Sejdic

This paper proposes a graph framework using pretrained SSL embeddings for speech analysis in Amyotrophic Lateral Sclerosis (ALS) patients, achieving better results than validation baselines on the SAN…

View →
cs.SDEmpiricalRecentJun 19, 2026

When EER Hides Deployment Failure: Auditing Threshold Transfer and Unlabeled Score Calibration for Speech Deepfake Detectors

Jingwen Zhou, Mingzhe Wang

This paper compares the performance of speech deepfake countermeasures using equal error rate (EER) and half total error rate (HTER) on different datasets. It also evaluates the effectiveness of popul…

View →
cs.SDcs.AIEmpiricalRecentJun 23, 2026

ZONOS2 Technical Report

Gabriel Clark, Sofian Mejjoute, Mohamed Osman, George Close +1 more

The authors present ZONOS2 8B, a TTS model with improved naturalness, prosody, and voice cloning fidelity, achieved through scaling, data expansion, and simplification.

View →
cs.SDcs.AIEmpiricalRecentJul 16, 2026

Large Audio Language Models for Spoofing-Aware Speaker Verification

Sofya Savelyeva, Mariia Perunova, Evgeny Kushnir, Artem Dvirniak +2 more

This paper evaluates the use of large audio language models for speaker verification systems against conventional pipelines and finds that task-specific adaptation improves performance.

View →
cs.SDcs.AIEmpiricalRecentJul 16, 2026

RW-Voice-EQ Bench: A Real World Benchmark for Evaluating Voice AI Systems

David Ayllon, Alice Baird, Jeffrey Brooks, Franc Camps-Febrer +10 more

The paper introduces the Real World Voice EQ Bench, a multidimensional benchmark for evaluating voice AI across text-to-speech, speech-to-speech, speech understanding, and automatic speech recognition…

View →
eess.ASEmpiricalRecentJul 2, 2026

Enhancing Acoustic-to-Articulatory Inversion with Multi-Target Pretraining for Low-Resource Settings

Jesuraj Bandekar, Prasanta Kumar Ghosh

This paper proposes a novel pretraining method for Acoustic-to-Articulatory Inversion (AAI) using Phoneme Labels, Articulatory Feature Labels, and Critical-articulator Labels, improving performance an…

View →
eess.AScs.SDEmpiricalRecentJun 21, 2026

Bridging Self-Supervised Learning and Speech Enhancement: A Wav2Vec2-Conditioned Framework

Shuubham Ojha, Carol Espy-Wilson

This paper conditions a diffusion-based speech enhancement model on wav2vec 2.0 features using Feature-wise Linear Modulation (FiLM), achieving competitive performance on VoiceBank-DEMAND and LibriMix…

View →
cs.CLcs.AIeess.ASRecentMay 31, 2026

PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects

Sicheng Yang, Shulan Ruan, Shiwei Wu, Yu Liu +3 more

PolySpeech-100 introduces a massive, multi-lingual benchmark covering 110 linguistic variants to rigorously test Speech-LLMs, demonstrating that open-source models struggle with low-resource languages…

View →
cs.CLcs.SDeess.ASEmpiricalRecentJun 18, 2026

Light-weight Pronunciation Assessment via Discrete Speech Token Surprisal

Syeda Faiza Ahmed Sara, Shammur Absar Chowdhury

A lightweight framework for automated pronunciation assessment using native speech resources and unsupervised or lightly calibrated methods.

View →
eess.ASEmpiricalRecentJun 12, 2026

Unsupervised Approaches for Global Prosodic Embedding Extraction

Martin Meza, Luciana Ferrer, Pablo Riera

The paper proposes methods for generating global prosodic embeddings using auto-encoder models of pitch and energy, demonstrating competitive or superior performance under challenging conditions.

View →