Applied & Human-Centered · Computer Science & AI
Sound
The newest papers in Sound that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
553 papers, from 4 September 2026 to 5 November 2026: 553 arXiv preprints.
Get the few papers worth your time in Sound every morning.
Follow Sound and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 15
Q-SPT: Learnable Query-Based Compression for Low-Frame-Rate Speech Tokenization
Neural speech codecs increasingly serve as tokenizers for speech language models (SLMs).AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language Models
Model intelligence and fast response jointly shape the quality of interaction with speech language models, yet remain difficult to achieve together.Exposing the Cost of Deep Learning Audio Development
The environmental impact of deep learning has attracted increasing attention over the past decade.Beyond Decodability: Do Acoustic Factors Drive Predictions in Speech-Based Alzheimer's Assessment?
Speech-based Alzheimer's disease (AD) assessments increasingly rely on pretrained self-supervised learning (SSL) models that learn acoustic representations directly from raw audio, exposing the…AVSD-Scenes: A Dataset for Audio-Visual Description of Urban Scenes
Natural language descriptions can provide rich semantic representations of audio-visual urban scenes, yet datasets that jointly describe both auditory and visual information remain limited.From Isolated Feature to Orbits: Discovering Music Concepts via Multi-SAE Alignment
How can we understand what a music foundation model has learned \textit{internally}?LAST: Looped Audio Spectrogram Transformer
Increasing depth of transformer models improves recognition, but it comes at a substantial cost.RAST: Resolution-Aware Privileged Structure Transfer for Low-Resolution Audio Activity Recognition
Audio is increasingly used for human activity recognition (HAR) because it captures object interactions, environmental events, and contextual cues in everyday environments.A barrier or a booster? Familiarity effects on Mandarin emotion prosody recognition using AI-powered voice cloning
Emotion prosody perception requires simultaneous processing of acoustic cues and speaker identity.Audio Token Attention Is Predictable Before the Language Model Runs
A large audio language model (LALM) turns a minute of speech into 750-1,500 tokens and prefills every one.FFASR: Benchmarking Far-Field Automatic Speech Recognition using High-Fidelity Simulated RIRs
Far-field automatic speech recognition(ASR) degrades under reverberation, noise, and talker motion, yet the benchmarks that drive model selection emphasize close-microphone speech.SCIC: Scope- and Codebook-Aware Instruction Conditioning for Speaker-Adapted Expressive TTS
Long-form live-streaming TTS requires context-dependent prosody and paragraph-level coherence.OP-CAD: On-Policy Clean-Audio Distillation for Robust Audio-Visual Reasoning
Omni-modal large language models deployed in real-world environments encounter external noise that can interfere with their perception and understanding of multimodal inputs.Training-Free Affinity Fusion of Neural and Embedding-Based Speaker Diarization
Speaker diarization systems based on speaker embeddings and neural diarization exploit complementary forms of speaker information, but their intermediate representations are not directly compatible.UniAE-MoE: A Unified Audio Encoder via Mixture of Experts
Large Audio Language Models (LALMs) rely on effective audio encoders for multi-task performance.Who Said What, and Will It Be Remembered? Evaluating Persistent Speaker Attribution Across Meetings
Speech transcripts used as long-term memory must preserve both words and stable speaker identities.From Speech to Editable Concepts: Probing Emotion Recognition with Concept Bottleneck Models
Speech emotion recognition (SER) is the task of assigning emotion labels to utterances.Ghost in the Encoder: Decodable Artist Identity Representations in Lyrics-to-Song Generation
Text-to-song generation models can be prompted to imitate specific artists or regurgitate entire songs from their training data.SE-ADD: Self-Evolving Audio Deepfake Detection with Mistake-Driven Supervision
Audio deepfake detection (ADD) must remain effective when new spoofing attacks emerge after deployment.SEAR: Spoofing Evidence-Grounded Audio Reasoning Benchmark for Audio Language Models
Audio language models (ALMs) are increasingly used for audio deepfake detection (ADD), yet existing benchmarks assess their verdicts or rationale plausibility without verifying the underlying…