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…

This paper systematically evaluates acoustic-to-articulatory inversion under domain shifts on FROST-EMA, a Finnish-Russian bilingual EMA corpus, and establishes benchmarks for articulatory targets, ac…

This paper introduces Re-Sonance, a real-time speech-driven AAC system for professional speaking scenarios using LLM-enhanced Whisper ASR, Qwen LLM, and CosyVoice TTS.

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

This paper introduces Audio BERT (AuB) and SpInv, methods for recovering embeddings from speech tokens and performing speaker inversion attacks using only three seconds of frontend output.

The paper proposes RTFree-F5, a method to make flow-matching TTS models like F5-TTS independent of reference transcripts, improving performance and naturalness for dysarthric speakers.

The study investigates the limitations of Phonetic Foundation Models (PFMs) for Speech-to-IPA transcription using Grapheme-to-Phoneme (G2P) labels and proposes a new approach based on continuous Artic…

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…

This paper proposes an SSL-AutoEncoder (SSL-AE) approach for reducing feature dimensions in self-supervised learning models while maintaining dysarthric ASR performance.

The paper describes a method to optimize the style vector for text-to-speech systems without a reference encoder, improving similarity and acceptance rate.

MindVoice is a neuro-to-speech framework that uses pretrained priors to disentangle and reconstruct intelligible speech from noisy, non-invasive neural signals, significantly outperforming existing me…

The paper introduces GigaSpeechBench, a comprehensive multilingual and multidimensional ASR & AST benchmark with 680 hours of human-annotated speech, featuring 12 low-resource languages, 6 Chinese dia…

The paper proposes a novel workflow to extract fine-grained regional accent features in Brazilian Portuguese using only acoustic labels and a phoneme-based forced aligner, showing that localized featu…

This paper investigates the use of various acoustic features for recognizing dysarthric speech using a Factorized Time Delay Neural Network (F-TDNN) model, achieving a relative improvement of 4.65% in…

The paper introduces three new Korean speech benchmarks (KVoiceBench, KOpenAudioBench, and KMMAU) to evaluate SpeechLMs, demonstrating that English-centric evaluation fails to capture performance gaps…