Speech & Audio

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…

ImmersiveTTS is an environment-aware text-to-speech model that generates natural speech seamlessly integrated within environmental contexts by explicitly modeling cross-modal interactions, achieving s…

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.

This paper proposes LoCA, a method to improve text-to-speech synthesis through local credit assignment and threshold-based regression control.

MOSS-Audio is a unified audio-language model designed for comprehensive understanding of speech, environmental sounds, and music, achieving strong performance across various audio-grounded tasks.

MelShield is a robust, in-generation audio watermarking framework that embeds identifiable signals into AI-generated speech in the Mel-spectrogram domain for reliable copyright protection and attribut…

The paper introduces a new inclusive, multimodal Hindi ASR benchmark with real-world recordings and diverse demographic groups, enabling more robust and realistic evaluation.

The paper introduces a novel Clean-Referenced Feature-Vocoder Attack, a black-box adversarial attack that perturbs high-level SSL feature representations instead of raw audio waveforms, achieving supe…

This paper evaluates four speech representation families for 3D facial synthesis and introduces an Audio Visual Text-to-Speech pipeline.

The paper proposes FineCombo-TTS, a unified framework for speech synthesis that enables flexible and precise control over acoustic attributes.

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 deconstruct the concept of naturalness in Text-to-Speech (TTS) evaluation into ten distinct perceptual dimensions and create a meta-evaluation benchmark for TTS systems using trained lingu…

This paper proposes a reinforcement learning approach for adapting audio-language models to code-switched speech using group relative policy optimization and verifiable rewards.

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.

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.

A text-to-speech model is trained to simulate the Lombard effect, improving clarity in noisy conditions.

This paper investigates whether combining multiple pre-trained speech encoders can improve speech-aware large language models for automatic speech recognition.

This paper proposes a watermark injection framework for text-to-speech systems that embeds a content-adaptive watermark into the generated representation.

The paper introduces Grounded Generative Speech Recognition (GSR), a reformulation of speech recognition as generating semantically grounded text instead of a single transcript.

The paper demonstrates that using on-policy distillation from a strong teacher model significantly improves the performance of compact Automatic Speech Recognition (ASR) models, achieving competitive…