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…

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 introduces DiaLLM, a method for continually pretraining language models on the International Corpus of English to generate dialectal English, and compares the effectiveness of different alig…

This paper demonstrates that compact, domain-specialized Automatic Speech Recognition (ASR) models significantly outperform large, general-purpose foundation models for conversational speech across 19…

The paper introduces CARTE, a new benchmark designed to test how well large language models understand fine-grained, regionally differentiated knowledge across the 13 metropolitan regions of France, r…

This paper fine-tunes two zero-shot text-to-speech models, Chatterbox and CosyVoice 3, on Singlish speakers from the IMDA National Speech Corpus to improve accent similarity and naturalness.

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

The paper proposes Pitch-Accent-focused Speech Quality Assessment (PASQA) to explicitly target pitch-accent correctness in speech quality assessment, using a controlled Japanese accent-error dataset a…

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…

A multimodal speaker identification system is proposed using Adaptive Modality Routing (AMR) for the POLY-SIM 2026 Grand Challenge, achieving high accuracy in various conditions.

The paper proposes a Lagrangian sub-flow (LSF) framework and geometric diagnostic signals to improve out-of-distribution detection using Continuous Normalizing Flows, overcoming the likelihood paradox…

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…

The paper introduces PS4, a framework for training target speaker extraction models using a large-scale corpus and proxy-supervised joint training strategy.

This paper investigates the effectiveness of incorporating synthetic speech data in Automatic Speech Recognition (ASR) Systems for three Indic languages by analyzing performance gains, script sources,…

This paper proposes a method for quantizing large language models with cross-layer error compensation and finite-sample feature-statistics matching.