~ similar to 2607.23027· 14 results
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…
Yujie Tu, Yifan Yang, Tianrui Wang, Yanqiao Zhu +32 more
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…
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.
Haechan Kim, Seungjun Chung, Inkyu Park, Jihoo Lee +1 more
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…
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…
Yuxiang Zhao, Yichi Zhang, Yanjie An, Yanqiao Zhu +9 more
X-Translator is a low-cost modular system for real-time speech-to-speech translation, using streaming ASR, machine translation, and prompt-conditioned TTS, with session-level control.
This paper examines the absence of phonological context compensation in wav2vec2.0 architecture using Mandarin Chinese tones, contrasting self-supervised pre-training with fine-tuning for ASR.
This paper investigates the ability of mean opinion score (MOS) prediction models to capture quality differences in text-to-speech beyond acoustic fidelity through controlled perturbations on speech.
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 demonstrates that compact, domain-specialized Automatic Speech Recognition (ASR) models significantly outperform large, general-purpose foundation models for conversational speech across 19…
The paper describes a method to optimize the style vector for text-to-speech systems without a reference encoder, improving similarity and acceptance rate.