May 2026
StepAudio 2.5 Technical Report
arXiv ↗Unified audio-language modeling has emerged as a prominent trend in modern speech systems, promising to bring the reasoning capabilities of large language models to auditory tasks.…
💛 42
📚 Awesome Speech Audio
12,389 papers across 0 tags, ranked by community signal and explained.
Jun 2026
One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time Applications
arXiv ↗Different real-time speech applications impose distinct latency budgets, often requiring separately trained enhancement models for each scenario. In this paper, we pro
💛 13
May 2026
SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue
arXiv ↗Zero-shot text-to-speech (TTS) has improved substantially for single-speaker synthesis, yet expressive long-form multi-speaker dialogue remains difficult. A common workaround is to…
💛 15
Mar 2026
Voxtral TTS
arXiv ↗We introduce Voxtral TTS, an expressive multilingual text-to-speech model that generates natural speech from as little as 3 seconds of reference audio. Voxtral TTS adopts a hybrid …
💛 61
May 2026
ChildVox: A Speech, Audio, and Large Audio-Language Model Benchmark in Understanding and Characterizing Sound across Childhood
arXiv ↗We present ChildVox, a novel benchmark for characterizing the diverse acoustic signals through which children communicate. Specifically, ChildVox follows the full developmental tra…
💛 5
Mar 2026
Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models
arXiv ↗As the paradigm of AI shifts from text-based LLMs to Speech Language Models (SLMs), there is a growing demand for full-duplex systems capable of real-time, natural human-computer i…
💛 36
Feb 2026
MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models
arXiv ↗Discrete audio tokenizers are fundamental to empowering large language models with native audio processing and generation capabilities. Despite recent progress, existing approaches…
💛 49
May 2026
Benchmarking Commercial ASR Systems on Code-Switching Speech: Arabic, Persian, and German
arXiv ↗Code-switching -- the natural alternation between two languages within a single utterance -- remains one of the most challenging and under-studied conditions for automatic speech r…
💛 2
Jan 2026
Qwen3-ASR Technical Report
arXiv ↗In this report, we introduce Qwen3-ASR family, which includes two powerful all-in-one speech recognition models and a novel non-autoregressive speech forced alignment model. Qwen3-…
💛 38
Apr 2026
T5Gemma-TTS Technical Report
arXiv ↗Autoregressive neural codec language models have shown strong zero-shot voice cloning ability, but decoder-only architectures treat input text as a prefix that competes with the gr…
💛 11
Mar 2026
SimulU: Training-free Policy for Long-form Simultaneous Speech-to-Speech Translation
arXiv ↗Simultaneous speech-to-speech translation (SimulS2S) is essential for real-time multilingual communication, with increasing integration into meeting and streaming platforms. Despit…
💛 15
Jul 2026
From Monolingual to Multilingual: Evaluating Mamba for ASR in South African Languages
arXiv ↗Recent advances in automatic speech recognition (ASR) have explored different sequence models, including Conformer-based models and newer state space models such as Mamba.
Jul 2026
Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving
arXiv ↗Speech-LLM integration has shown promising results by leveraging extensive textual pretraining, yet its specific benefits for automatic speech recognition (ASR) remain u
Jul 2026
NAVER LABS Europe Submission to the Instruction-following 2026 Short Track
arXiv ↗In this paper, we describe NAVER LABS Europe's submission to the instruction-following speech processing short track at IWSLT 2026. We participate again in the constrained
Jul 2026
Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning
arXiv ↗Instruction tuning for speech language models (SLMs) is substantially more challenging than for text-based large language models (LLMs), as it requires learning a new mo
Feb 2026
PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models
arXiv ↗Recent advances in duplex speech models have enabled natural, low-latency speech-to-speech interactions. However, existing models are restricted to a fixed role and voice, limiting…
💛 9
Mar 2026
MOSS-TTS Technical Report
arXiv ↗This technical report presents MOSS-TTS, a speech generation foundation model built on a scalable recipe: discrete audio tokens, autoregressive modeling, and large-scale pretrainin…
💛 13
Jul 2025
Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
arXiv ↗We present Audio Flamingo 3 (AF3), a fully open state-of-the-art (SOTA) large audio-language model that advances reasoning and understanding across speech, sound, and music. AF3 in…
📚 189
Feb 2026
Covo-Audio Technical Report
arXiv ↗In this work, we present Covo-Audio, a 7B-parameter end-to-end LALM that directly processes continuous audio inputs and generates audio outputs within a single unified architecture…
💛 15
Jul 2026
Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis
arXiv ↗Flow Matching (FM) has emerged as a powerful paradigm for speech generation but remains constrained by high inference latency and timbre leakage. To address these bottlene
Jul 2026
A Geometric Perspective on Composable Emotion Steering in Text-to-Speech Models
arXiv ↗While prior work has explored emotion control in hybrid text-to-speech systems, the geometric properties of these modules, and their implications for steerability, remain
Jul 2026
Quantifying the Uncertainty of Blindly Estimated Room Embeddings Using a Dispersion-Calibrated Score
arXiv ↗Room embeddings derived from reverberant speech are often unreliable: speech content and recording degradation can alter the representation even when speaker, room, and so
Jul 2026
Beyond Words: Towards Effective Modeling of Non-Verbal Vocalizations in ASR
arXiv ↗Modern automatic speech recognition (ASR) systems excel at transcribing lexical content but often omit nonverbal vocalizations (NVs), such as laughter, breaths, coughs, an
Jul 2026
H-SAGE: Holistic Speaker-Aware Guided Experts for MoE-based Multi-Talker ASR
arXiv ↗Multi-talker Automatic Speech Recognition (MTASR) faces significant challenges in accurately transcribing overlapping speech, particularly under complex high-overlap condi