This paper proposes a voice concept bottleneck framework for interpretable health assessment using an audio language model.

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 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 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…

The paper introduces SURE, a unified framework designed to standardize and improve the comparability and reproducibility of evaluations for advanced speech understanding models.

This paper investigates the correlation between dimensions of self-supervised speech features and speech characteristics, finding that content dimensions primarily capture intensity, formants, and voi…

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

The paper introduces a phoneme-level analysis framework for interpreting speech deepfake detection results using Gradient-weighted Class Activation Mapping and speech recognition.

This paper compares the effectiveness of classical and neural speech codecs using P.808 and P.800 DCR tests in crowdsourced and conventional evaluations. It proposes suitable screening methods for imp…

This paper investigates the relationship between language model perplexity and word error rate in modern automatic speech recognition systems, studying the impact of external language models, encoder…

The authors identify confusion patterns in a large audio-language model and use them to curate diagnostic data for fine-tuning, achieving higher accuracy than the baseline.

The paper repurposes a pre-trained speech classifier as the backbone for diffusion generation, reducing the need for two separately trained models.

This paper proposes a data-driven method for automatic blind audio equalization using a deep neural network and semantic embeddings.

The paper introduces OpenSTBench, a unified, multidimensional evaluation framework designed to comprehensively compare heterogeneous speech translation systems by jointly assessing translation, speech…

The paper proposes a multi-axis evaluation framework for structured audio descriptions using a controlled perturbation testing protocol.

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,…

The paper introduces Dialogs, a new Russian conversational speech corpus with high-quality recordings, segmented utterances, and expressive prosody labels.