001 TDScore: Learning Synthetic Speech Quality Predictors from TTS Training Dynamics without Human annotation OpenAlex Paper Natacha Miniconi, Meysam Shamsi et al. Sep 27 002 Multiresolution Neural Network for One-Class Learning of Machine Sounds OpenAlex Paper Xiran Zhang, Vincent Lostanlen et al. Aug 31 003 A Framework for the Automation of Preference Grammar OpenAlex Paper C.U.C. Ugorji, Ginikachi Maduako et al. 4 days ago 004 The Genealogy of Large Language Models: From Auxiliary Tools in ASR to Foundational Transformers and Back Again OpenAlex Paper José Luciano Maldonado 4 days ago 005 Parameter-Efficient Fine-Tuning: LoRA, QLoRA, and DoRA OpenAlex Paper Dheiver Francisco Santos 5 days ago 006 Parameter-Efficient Fine-Tuning: LoRA, QLoRA, and DoRA OpenAlex Paper Dheiver Francisco Santos 5 days ago 007 Synthetic Data Generation and Self-Improvement: A Technical Note OpenAlex Paper Dheiver Francisco Santos 5 days ago 008 Synthetic Data Generation and Self-Improvement: A Technical Note OpenAlex Paper Dheiver Francisco Santos 5 days ago 009 A lightweight hybrid 2D–1D depthwise-separable CNN with frequency-only pooling for efficient small-footprint keyword spotting OpenAlex Paper Jaewon Lee, Sangbeom Lee et al. 6 days ago 010 LiveLingo Voice Translation Benchmarks 2026 OpenAlex Paper Ron Villomo 6 days ago 011 A Deep Learning based Approach for Identifying Spoken languages in Turkey OpenAlex Paper Müge Ertekin, Hamit Erdem 7 days ago 012 Embedding-Guided Neural Voice Conversion for Indian Regional-Language Speech Transformation OpenAlex Paper Bala Raju A, Singh S.P et al. 7 days ago 013 How Meta-Learning Shapes LoRA Adapter Geometry in Speech Deepfake Detection OpenAlex Paper Ivan Kukanov, Janne Laakkonen et al. 7 days ago 014 Quality-Targeted, Page-Aligned KV-Cache Allocation for LLM Inference OpenAlex Paper Athanase Matabaro 7 days ago 015 Quality-Targeted, Page-Aligned KV-Cache Allocation for LLM Inference OpenAlex Paper Athanase Matabaro 7 days ago 016 Run inference OpenAlex Paper Yahya Saqban 7 days ago 017 Run inference OpenAlex Paper Yahya Saqban 7 days ago 018 hearth-llm: Persistent KV-Cache Snapshots for Interactive Local LLM Inference OpenAlex Paper Foromo Daniel Soromou 7 days ago 019 hearth-llm: Persistent KV-Cache Snapshots for Interactive Local LLM Inference OpenAlex Paper Foromo Daniel Soromou 7 days ago 020 From Read Speech to Spoken Digits: A Task-Specific Evaluation of Speech Privacy With Informed Attackers OpenAlex Paper Jule Pohlhausen, Anjana Rajasekhar et al. Jul 23 021 Toward Interpretable Speech Deepfake Detection using Artifact-Specific Experts and Calibrated Detection Scores OpenAlex Paper Viola Negroni, Xin Wang et al. Jul 23 022 Improving the performance of an ASV system using hybrid speech features OpenAlex Paper Stanisław Ciszkiewicz, Artur Janicki Jul 22 023 Multimodal Speaker Verification as a Threat to Speaker Anonymization OpenAlex Paper Ashi Garg, Cristina Aggazzotti et al. Jul 22 024 Scalable Keyword Spotting via Modular Network Expansion OpenAlex Paper Viktor Khaymonenko, Dzmitry Saladukha et al. Jul 22 025 SimulS2ST-Omni: Data-Efficient Streaming Speech-to-Speech Translation via Explicit Trajectory Supervision OpenAlex Paper Rong‐De He, C X Liang et al. Jul 22 026 StellarTTS: Sparse Temporal Embedding for Low-Latency and Robust Speech Synthesis OpenAlex Paper Kaicheng Luo, X Z Gong et al. Jul 22 027 A Multi-Stage Poisoning Detection Pipeline for Embedded Voice-Command Systems OpenAlex Paper Sebastian–Alexandru Drăguşin, Denisa Toma et al. Jul 21 028 Edge-based danger detection system using phrase recognition on STM32 microcontroller with FreeRTOS and GSM communication OpenAlex Paper Ho Yen Rou, Hermawan Nugroho Jul 21 029 Frequency-based Rerpesentation Consistency Regularization for Dense Retrieval OpenAlex Paper Hongyeob Kim, Seoyoon Lee et al. Jul 21 030 Speech-GAN: A Black-Box Generative Adversarial Network Attack against Automatic Speech Recognition systems OpenAlex Paper Faraz Mohammad Mushtak Mogal, Ali Osman Topal et al. Jul 21 031 Summary of DCASE 2026 Task 5: Audio-Dependent Question Answering OpenAlex Paper Haolin He, Renhe Sun et al. Jul 21 032 AM-DANet: Additive margin with dynamic augmentation network for speaker identification OpenAlex Paper Jing Xiang Ng, Kian Ming Lim et al. Jul 20 033 Enhancing Low-Resource Lampung Speech Recognition through Cross-Lingual XLSR-Wav2Vec 2.0 Pretraining OpenAlex Paper Hendra Kurniawan Jul 20 034 Harness TTS: Towards Context-Aware Expressive Speech Synthesis with Harness Layer OpenAlex Paper Shengfan Shen, Di Wu et al. Jul 20 035 SSTMark: Robust Training-Free Semantic-Level Speech Watermarking OpenAlex Paper Kuan-Lin Chu, Jun-Cheng Chen et al. Jul 20 036 The tttAI System for the TSA-ASR Task of the SmartGlasses Challenge 2026 OpenAlex Paper Xuanji He, Gaoyang Dong et al. Jul 20 037 Tibetan language model incorporating grammatical relationships and morphological verbs OpenAlex Paper Kuntharrgyal Khysru, Wenjie Tang et al. Jul 20 038 X-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System OpenAlex Paper Yuxiang Zhao, Yichi Zhang et al. Jul 20 039 Choosing the Compute Unit for On-Device Speech Recognition: NPU, GPU and CPU in a Single Pipeline OpenAlex Paper Alexander Dmitriev Jul 19 040 Choosing the Compute Unit for On-Device Speech Recognition: NPU, GPU and CPU in a Single Pipeline OpenAlex Paper Alexander Dmitriev Jul 19 041 Mixed approach speech-to-text translation for endangered language OpenAlex Paper Benyamin Langgu Sinaga, Stephanie Pamela Adithama et al. Jul 18 042 NABEATs: Noise-Aware Audio Representation Learning OpenAlex Paper Takuya Fujimura, Yoshiki Masuyama et al. Jul 18 043 A Geometry-Limited Identification Floor and Its Consequences for Voice-Clone Attribution in Professional Voice Actors OpenAlex Paper Shuhei Kato Jul 17 044 AMECxSV: Adaptive Metadata-Driven Embedding-Fusion Calibration for X-Lingual Speaker Verification OpenAlex Paper Xin Wei, Shi He et al. Jul 17 045 Bsqat: block-wise shared quantization-aware training for large language models OpenAlex Paper Senbao Hou, Libin Hou et al. Jul 17 046 COMPOSITIONAL RECOGNITION OF AZERBAIJANI SPEECH SIGNALS USING PHONETIC ACOUSTIC COMPONENTS OpenAlex Paper Elchin Ismayilov Jul 17 047 Component-Level Ensemble Fusion for Speech and Environmental Sound Deepfake Detection OpenAlex Paper André Runewicz, Karla Schäfer et al. Jul 17 048 Natural Language Processing (NLP) for Speech Recognition and Text-to-Speech OpenAlex Paper Amrutha Kolhar, Tukkappa K. Gundoor Jul 17 049 Problems of Artificial Intelligence for the Azerbaijani Language: The Impact of Limited Language Corpus OpenAlex Paper Raksana Aliashrafova, Namiq Abdurahmanov et al. Jul 17 050 Real-Time Speech-to-Text And Speaker Diarization Using Whisper And Pyannote Embeddings OpenAlex Paper Shivani Chauhan, Rimmy et al. Jul 17 051 Real-Time Speech-to-Text And Speaker Diarization Using Whisper And Pyannote Embeddings OpenAlex Paper Shivani Chauhan, Rimmy et al. Jul 17 052 The Symboken Theory OpenAlex Paper IHARA Jul 17 053 The Symboken Theory OpenAlex Paper IHARA SHUHEI, SHUHEI IHARA Jul 17 054 A Lightweight Keyword Spotting Method Using a Convolutional Spiking Neural Network with Learnable Synaptic Delays OpenAlex Paper X W Li, Ying Liu et al. Jul 16 055 Audio Deepfake Detection using Cepstral Coefficients and Spectral Analysis OpenAlex Paper Prapti Kapoor Jul 16 056 Audio Deepfake Detection using Cepstral Coefficients and Spectral Analysis OpenAlex Paper Prapti Kapoor Jul 16 057 Effects of applying Gaussianising transformations to DNN embeddings before calculating likelihood ratios OpenAlex Paper Rafael O. Ribeiro, Philip Weber et al. Jul 16 058 SLT 2026 REAL-TSE Challenge: Real-world Target Speaker Extraction from Conversational Recordings OpenAlex Paper Shuai Wang, Zihan Qian et al. Jul 16 059 <p>Cultural and Linguistic Contextualization in Ugandan English: Training Transformer Models for Enhanced Local Relevance</p> OpenAlex Paper David Byansi, Bebwa Isingoma et al. Jul 15 060 A survey of forensic practitioners on speaker attribution methods OpenAlex Paper Tallulah Buckley, Kirsty McDougall et al. Jul 15