Engineering & Signals · Interdisciplinary & Society
Audio & Speech Processing
The newest papers in Audio & Speech Processing that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
334 papers, from 8 September 2026 to 4 November 2026: 334 arXiv preprints.
Get the few papers worth your time in Audio & Speech Processing every morning.
Follow Audio & Speech Processing 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
SAUCE: Summary Analysis Using Conversation Entailment
With the growing need for evaluating Large Language Models (LLMs) and their applications to speech, challenges persist in summarizing and evaluating conversations that lack a clear end goal.ReListen: Training-Free Evidence Localization in Hour-Long Audio with Frozen Audio Language Models
Audio language models are meant to answer questions from the audio itself, but an hour-long recording rarely fits in their context, and the answer often depends on a few seconds of it.Spatial Transfusion: From Structured Spatial Scene Understanding to Generation and Editing
Spatial audio conveys not only what sounds are present, but where they originate and how they interact with the environment.Deployment-constrained key estimation with a DSP-guided transformer reranker
Local music applications estimate key during library import and benefit from an analyzer that is small, fast, and runs in-process.InteractionBench: Measuring Timing, Task Accuracy, Whisper and Volume, and Grounding in Real-Time Voice Systems
Most benchmarks for real-time voice systems focus on one aspect, such as turn-taking, instruction following, paralinguistic control, or conversational memory, each with its own data and set of…VioTech: Frame-Level Violin Playing Technique Detection with Multi-Scale Mixture-of-Experts
Playing technique is crucial for expressive violin performance, yet few violin technique detection models exist.Voice-Native LLMs Hear Frustration but Do Not Listen to It
Users convey frustration in what they say and in how they say it, and voice-native models, which hear speech instead of an ASR transcript, can register both.ufakzeka-kulak: Building and Evaluating a 31.6M-Parameter Turkish Speech Recognizer from Scratch
ufakzeka-kulak is an open Turkish speech-to-text model of 31.6M parameters, a FastConformer encoder with a token-and-duration transducer (TDT) and a CTC head, trained from scratch and released under…Metadata-Conditioned Audio Transformers for Adaptive Respiratory Sound Classification
Respiratory sound classification from auscultation recordings is confounded by heterogeneous acquisition conditions, including recording device, auscultation site, and patient characteristics, that…Local or Escalate? Post-Training Expert Routing for Real-Time Duplex Speech Models
A full-duplex model should answer easy questions immediately, but hard questions often need stronger reasoning, which may require waiting.Wave Physics as Representation: Tensor-Structured Neural Reconstruction for Ocean Acoustic Fields
Reconstructing three-dimensional (3D) complex ocean acoustic fields from sparse measurements is challenging due to highly oscillatory wave structures and restricted sensing patterns/routes.MEX: The Musical Expectation Benchmark Suite
We propose the Musical Expectation (MEX) benchmark suite for perceptually validating computational models of musical expectation, i.e., models that estimate music information dynamics (MID) measures…Spatial DJ: Spatial Audio Control for Arbitrary Loudspeaker Layouts
Object-based spatial audio promises render-anywhere playback, yet deploying it in a new venue still requires two tasks that are rarely addressed together: acquiring the physical loudspeaker geometry…Learning Timeline-Preserving Speech-to-Speech Translation
Speech-to-speech translation (S2ST) increasingly preserves what is said and how it sounds, but not necessarily when speech and silence occur.ResMamba: A Dual-Path Convolution-Mamba Model for Music Genre Classification
Music genre classification remains a fundamental yet challenging task in music information retrieval, requiring models that capture local time--frequency patterns and long-range temporal dependencies.Microphone Geometry Aware Regional Target Speaker Extraction
Regional target speaker extraction (RSE) aims to extract speech originating from a specified angular region, relaxing the requirement for precise target speaker location when performing location…How Close to the Theme? Similarity-Label Conditioning for Game Music Generation
Composers develop music from an original idea, controlling how similar each new section is to it, from near repetition to new material.Pop Goes the Verifier: Phoneme-Targeted Data Poisoning of Voice Liveness Detection
Many Automated Speaker Verification Systems (ASVs) commonly employ liveliness detection techniques, such as VoicePop, which identify genuine speech by analyzing low- frequency pop bursts from…GSLM2: Multi-Stream Speech Representation Learning and Generative Spoken Language Modeling
Generative spoken language models (SLMs) offer a route to learning linguistic structure purely from speech, yet they lag far behind text-based models in both capability and data scaling efficiency.NepTTS-Bench: Native-Speaker Benchmarking and NepaliMOS for Nepali Text-to-Speech
Nepali TTS has reached a point where multiple systems are available, but there is no shared evaluation to compare them.