Latest Speech Recognition Research Papers

The newest Speech Recognition papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Speech Recognition so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• Transformation of Sub-Discourses of Women’s Socio-Political Activism after the Islamic Revolution: A Critical Discourse Analysis of Selected Activists
  Zahra Korayi, Yousef amini, احمدعلی حسابی, Amir Ali Dorosti · Journal of Historical Resea... · Nov 1, 2026

  This study, grounded in the framework of critical discourse analysis and employing a hybrid model of Norman Fairclough alongside the discourse theory of Ernesto Laclau and Chantal Mouffe, examines the transformation of sub-discourses of wom…

• Toward Complete Speaker Anonymization: a Streaming Cascaded System for Voice Privacy and PII Removal
  Stanisław Kacprzak, Thomas Thebaud, Najim Dehak · arXiv · Oct 29, 2026

  We present a cascade streaming voice privacy system, consisting of ASR, NLP, and TTS modules. By leveraging recent improvements in all three aspects of speech and language processing, we show that such a system is capable of achieving a res…

• Reading-Level Verification of Kanji Words in Japanese Financial Speech Synthesis
  Cheng Zhang · arXiv · Oct 29, 2026

  Few-shot voice cloning makes it cheap to produce daily Japanese financial commentary with several synthetic speakers, but kanji words with more than one reading, such as the word for "market" (shijo vs. ichiba) or "overall trend" (taisei vs…

• How Architecture, Typology, and Adaptation Strategies Shape ASR for Low-Resource African Languages: A Controlled Empirical Study
  Mercy Muchai, Kevin Chege, Nick Mumero Mwangi, Samuel Chege Maina et al. · arXiv · Oct 28, 2026

  Despite recent advancements in ASR, identifying effective architectures, fine-tuning approaches, and data adaptation strategies for low-resource languages remains challenging. We present a systematic comparison across five low-resource Afri…

• Wav2Aug: A Drop-In Speech Augmentation Policy
  Gianfranco Dumoulin Bertucci, Mirco Ravanelli · arXiv · Oct 28, 2026

  SpecAugment is the dominant speech augmentation policy, but researchers have studied it primarily for automatic speech recognition (ASR), and it operates on spectrograms, limiting its applicability to other speech tasks and waveform models.…

• Do Audio LLMs HEAR Pain? Tracing Acoustic Evidence from Speech to Language Reasoning
  Wenqi Li, Xiangjue Dong, Sulaiman Vesal · arXiv · Oct 28, 2026

  Large audio language models (LALMs) can process speech directly, but it remains unclear how well they use the non-lexical acoustic information that speech carries. We study this question through pain, using TAME-Pain, which contains pain-ne…

• ASR-Mediated Speaking Practice for Lower-Proficiency University EFL Learners: Perceptions across Novice and Beginner Levels
  Ye-Eun Kwon · Secondary English Education · Oct 28, 2026

  Although automatic speech recognition (ASR) has been increasingly used in L2 speaking instruction, relatively little is known about how lower-proficiency learners perceive sustained ASR-mediated speaking practice. This study investigated th…

• From Voiceprints to User Entities: Online Speaker-Memory Construction for Multi-User Spoken Agents
  Yucong Zhang, Cancan Li, Bo Xiao, Ke Zeng et al. · arXiv · Oct 27, 2026

  Personalized spoken agents must identify speakers before accessing user-specific memory, yet memory benchmarks typically assume correctly attributed histories. We argue that voiceprints are observations of identity, not identities themselve…

• Integrate the Reward, Don't Sample It: Window Likelihood for Interruptions and Backchannels in Full-Duplex Speech Models
  Guoqiang Hu, Lichao Zhang, Yizhou Peng, Yuhao Luo et al. · arXiv · Oct 26, 2026

  A full-duplex spoken dialogue model must yield when the user cuts in and hold when the user merely backchannels. Sequence-level RL with a timing reward (GRPO) is the usual recipe; we test its whole-rollout form on four open models and find …

• ASR-Protected Fusion and Reference-Anchored Policy Optimization for Joint ASR and Word-Level Speech Anti-Spoofing
  Xueping Zhang, Xiaoxiao Miao, Tiantian Feng, Ming Li · arXiv · Oct 25, 2026

  Existing anti-spoofing systems report either an utterance-level score or a time-based spoof interval: the former cannot show which words are spoofed, while the latter does not directly match the transcript and must be post-aligned with word…

• Measuring the Verifier's Floor: How Much Apparent Rare-Word Text-to-Speech Error Is ASR Error?
  Kirill Borodin, Vasilii Kudryavtsev, Nikita Vasiliev, Grach Mkrtchian · arXiv · Oct 22, 2026

  Text-to-speech (TTS) is usually evaluated by transcribing its output with an automatic speech recognition (ASR) system, so the word error rate also counts recognizer errors. We measure these errors on human recordings of the test sentences.…

• Synthetic-to-Real Code-Switched ASR: A Spontaneous Nepali-English Podcast Benchmark
  Firoj Paudel · arXiv · Oct 22, 2026

  Nepali-English code-switched conversational speech presents severe challenges for automatic speech recognition (ASR), chiefly through script confusion (inappropriate mixing of Devanagari and Latin orthography) and elevated error rates at la…

• Text-Only LLM Correctors Break Correct Transcripts: A Repair-Damage Analysis of Audio Grounding in ASR Error Correction
  Vasiliy Kudryavtsev, Kirill Borodin, Nikita Vasiliev, Mikhail Gorodnichev et al. · arXiv · Oct 21, 2026

  LLM correctors of ASR output are judged by aggregate WER, which hides what they fix and what they break. We decompose every WER change exactly into repaired tokens, damaged tokens and insertions, and use this to ask what the source audio ad…

• Bio-Inspired Auditory Processing: Coupling Parallel Resonate-and-Fire Dynamics with Ternary Recurrent Networks for Speech Recognition
  Pavlos Poulos, Katelyn Sadorf, Themos Stafylakis, Costas A. Anastassiou · arXiv · Oct 21, 2026

  Spiking Neural Networks (SNNs) promise energy-efficient inference through sparse, event-driven computation, yet remain constrained on continuous, context-dependent tasks such as automatic speech recognition (ASR). A key bottleneck is the Le…

• Bio-Inspired Auditory Processing: Coupling Parallel Resonate-and-Fire Dynamics with Ternary Recurrent Networks for Speech Recognition
  Pavlos Poulos, Katelyn Sadorf, Themos Stafylakis, Costas A. Anastassiou · arXiv · Oct 21, 2026

  Spiking Neural Networks (SNNs) promise energy-efficient inference through sparse, event-driven computation, yet remain constrained on continuous, context-dependent tasks such as automatic speech recognition (ASR). A key bottleneck is the Le…

• Qwen-Audio-3.1-ASR Technical Report
  Chuanmeng Bian, Daren Chen, Peixin Chen, Zhigao Chen et al. · arXiv · Oct 20, 2026

  We present Qwen-Audio-3.1-ASR, a family of audio-language models that builds upon its predecesor Qwen-Audio-3.0-ASR with improved speech recognition and expanded capabilities in speaker-diarized transcription and general audio understanding…

• Improved automatic speech-based cognitive assessment using neuropsychologically calibrated diagnostic labels
  Madhurananda Pahar, Caitlin Illingworth, Adam Hampshire, Peter J Hellyer et al. · arXiv · Oct 20, 2026

  Although automatic detection of cognitive impairment from conversational speech is a promising way, it becomes less accurate, as large real-world datasets often contain unreliable diagnostic labels due to self-referral and limited clinical …

• Uncovering Audio-Text Alignment in Large Audio-Language Models through Cross-Modal Concept Neurons
  Tzu-Quan Lin, Chih-Kai Yang, Yi-Cheng Lin, Hao Tang et al. · arXiv · Oct 20, 2026

  While the language model backbone is pretrained on text alone, large audio-language models (LALMs) can, to a great extent, recognize acoustic attributes, such as emotion, speaker gender, and spoken language. However, it is unclear how the a…

• AAC Access and Interventions for Children with Motor and Speech Disabilities
  Dawn J. Sowers, Savanna Brittlebank, Krista M. Wilkinson · Current Developmental Disor... · Oct 20, 2026

  Abstract Purpose of Review Children with motor and speech disabilities represent a heterogeneous group who can benefit substantially from augmentative and alternative communication (AAC). AAC technologies have been shown to support spoken l…

• Preference-Aware Pareto Steering for Multi-Task Speech LLMs
  Liuyuan Jiang, Vishal Sunder, Samuel Thomas, Brian Kingsbury et al. · arXiv · Oct 19, 2026

  Speech large language models (LLMs) perform multiple tasks, including automatic speech recognition (ASR), timestamp prediction (TS), and speech translation (ST). Joint training of speech LLMs creates task trade-offs, yet standard training w…

• Beyond Two Tracks: Speaker-Anchored Full-Duplex Dialogue Recovery
  Yuxuan Chen, Yang Xiao, Jack Sun, Chak Sun et al. · arXiv · Oct 19, 2026

  Spoken interaction is moving from alternating turns to full-duplex conversation, where an agent listens while speaking. Learning this coordination requires natural dialogue with persistent speaker-resolved tracks, a data requirement that re…

• TeleASR-Amharic: A Benchmark for Robust Amharic ASR in Realistic Telecommunication Conditions
  Dagnachew Mekonnen Marilign, Enrique Molero, Abrham Haile, Louis Powell et al. · arXiv · Oct 19, 2026

  The real-world usability of ASR models remains challenging, particularly for low-resource languages, where existing speech resources are often collected in clean studio environments. In this work, we introduce TeleASR-Amharic, a benchmark f…

• PERFORMANCE ENHANCEMENT FOR MOUTH DETECTION TIME BASED ON MODIFIED VIOLA-JONES ALGORITHM
  Mohammed E. Safi, Eyad I Abbas, Alaa H. Ali · Science Journal of Universi... · Oct 19, 2026

  Mouth detection is an important issue in visual speech recognition. The de facto algorithm used to achieve this is the Viola-Jones algorithm. Nevertheless, time enhancement for the auto-detection of this algorithm is required. Therefore, th…

• VoicePay: A Smart Controlled Payment Application using Voice Commands Secure, Accessible and Limit-Aware Digital Payments through Speech
  Prof.Savita Biradar · Zenodo (CERN European Organ... · Oct 18, 2026

  The rapid growth of digital payments has increased the need for payment methods that are fast, accessible and secure. This paper presents VoicePay, a smart controlled payment application that lets users start and approve transactions throug…

• Dual Task Vector Merging: Leveraging Emotion and ASR Knowledge for Low-Resource Alzheimer's Disease Detection
  Yuan-Chao Li, Yin-Long Liu, Liu He, Sizhe Liu et al. · arXiv · Oct 17, 2026

  Alzheimer's Disease (AD) detection from speech benefits from both paralinguistic and linguistic cues, yet model training is frequently constrained by limited data. Fine-tuning a large pretrained speech encoder can easily overfit, while a fr…

• ShlokaDhara: A Multi-Speaker Sanskrit Speech Corpus for Learning Meter-Aware Prosody in Text-to-Recitation
  Harshal Kausadikar, Onkar Kishor Susladkar, Prathmesh Santosh Choudhari, Vedangi Deepak Deshpande et al. · arXiv · Oct 17, 2026

  Sanskrit verse recitation is governed by $\textit{Chandas}$, a strict prosodic framework defined by rhythmic $\textit{Laghu}$ (light) and $\textit{Guru}$ (heavy) syllables. Because existing Sanskrit speech datasets prioritize ASR or convers…

• ASR Personalization in Pathological Voice: Accuracy, Efficiency, and Duration Effects
  Giuseppe Giaimis, Sergei Katkov, Muhammad Azfar Yaqub, Antonio Liotta · Science · Oct 17, 2026

  Automatic Speech recognition (ASR) struggles with Pathological speech due to persistent speaker-specific mismatch. In clinical and accessibility scenarios, only limited target-speaker data is typically available, making full model retrainin…

• VocalGrad: Evaluating Acoustic Perception in Audio Language Models
  Koki Ryu, Hitomi Yanaka · arXiv · Oct 16, 2026

  Recent large audio language models (LALMs) have extended their capabilities beyond lexical speech understanding to tasks requiring paralinguistic and non-linguistic audio understanding, such as emotion recognition. However, these models sti…

• Flash RNN-T: Memory-Efficient Joint Network and Transducer Loss Computation
  Mahmoud Ashraf · arXiv · Oct 16, 2026

  The recurrent neural network transducer (RNN-T) remains a practical choice for streaming speech recognition, but training requires large intermediate tensors. We present Flash RNN-T, a joint and loss implementation combining specialized ker…

• Advancing Sentence-Level Dysarthric Audio-Visual Speech Recognition via Test-Time Adaptation
  Shiyao Wang, Hui Wang, Jiaming Zhou, Shiwan Zhao et al. · arXiv · Oct 16, 2026

  Dysarthric audio-visual speech recognition (DAVSR) enhances performance by integrating complementary visual cues. However, existing research is largely confined to word-level tasks with limited vocabularies, which severely restricts real-wo…