Contextual speech recognition

Συγγραφείς: Woodward Riquelme, Alejandro Benjamín

Συνεισφορές: University/Department: Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions

Thesis Advisors: Marqués Acosta, Fernando, Varas González, David

Πηγή: TDX (Tesis Doctorals en Xarxa)

Θεματικοί όροι: Automatic Speech Recognition, Speech Recognition, Contextual Speech Recognition, Deep Neural Networks, Attention, Àrees temàtiques de la UPC::Enginyeria de la telecomunicació, 621.3 - Enginyeria elèctrica. Electrotècnia. Telecomunicacions

Περιγραφή αρχείου: application/pdf

Σύνδεσμος πρόσβασης: http://hdl.handle.net/10803/695052
https://dx.doi.org/10.5821/dissertation-2117-439777

Evolutionary Prompt Design for LLM-Based Post-ASR Error Correction

Συγγραφείς: Sachdev, Rithik, Wang, Zhong-Qiu, Yang, Chao-Han Huck

Πηγή: 2025 IEEE Workshop on Signal Processing Systems (SiPS) Signal Processing Systems (SiPS), 2025 IEEE Workshop on. :1-5 Nov, 2025

Relation: 2025 IEEE Workshop on Signal Processing Systems (SiPS)

Open Source State-Of-the-Art Solution for Romanian Speech Recognition

Συγγραφείς: Pirlogeanu, Gabriel, Georgescu, Alexandru-Lucian, Cucu, Horia

Πηγή: 2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD) Speech Technology and Human-Computer Dialogue (SpeD), 2025 International Conference on. :102-107 Oct, 2025

Relation: 2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)

Impact of Text Origin and Real-Synthetic Data Ratio in TTS-Augmented Low-Resource ASR

Συγγραφείς: Mengke, Dalai, Wuyerigen, Mihajlik, Peter

Πηγή: 2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD) Speech Technology and Human-Computer Dialogue (SpeD), 2025 International Conference on. :97-101 Oct, 2025

Relation: 2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)

Securing Automatic Speech Recognition with Attention-driven Adversarial Detection

Συγγραφείς: Rehman, Muhammad Zia Ur, Rashid, Muhammad Ehtisham, Khan, Murad

Πηγή: 2025 7th International Conference on Blockchain Computing and Applications (BCCA) Blockchain Computing and Applications (BCCA), 2025 7th International Conference on. :906-911 Oct, 2025

Relation: 2025 7th International Conference on Blockchain Computing and Applications (BCCA)

Generalization in Audio Deepfake Detection: Evaluating ASR Encoder-Based Feature Extraction

Συγγραφείς: Schafer, Karla, Steinebach, Martin

Πηγή: 2025 IEEE 12th International Conference on Data Science and Advanced Analytics (DSAA) Data Science and Advanced Analytics (DSAA), 2025 IEEE 12th International Conference on. :1-5 Oct, 2025

Relation: 2025 IEEE 12th International Conference on Data Science and Advanced Analytics (DSAA)

'Alexa, what do you mean to me?': a scoping review and model of parasocial relationship formation with smart speakers.

Συγγραφείς: Griffin, Charlotte Elizabeth¹ (AUTHOR) cgriffin3@glos.ac.uk, Powell, Georgina¹ (AUTHOR)

Πηγή: Behaviour & Information Technology. Nov2025, Vol. 44 Issue 19, p4796-4822. 27p.

Θεματικοί όροι: *AUTOMATIC speech recognition, *RESEARCH funding, *ARTIFICIAL intelligence, *DESCRIPTIVE statistics, *INTERPERSONAL relations, *USER interfaces, AT-risk people, AGE distribution, SYSTEMATIC reviews, THEMATIC analysis, CONCEPTUAL structures, SOCIAL isolation

Tiny-Align: Bridging Automatic Speech Recognition and Large Language Model on Edge

Συγγραφείς: Qin, Ruiyang, Liu, Dancheng, Xu, Gelei, Nassereldine, Amir, Yan, Zheyu, Xu, Chenhui, Hu, Yuting, Hu, X. Sharon, Xiong, Jinjun, Shi, Yiyu

Πηγή: 2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD) Computer Aided Design (ICCAD), 2025 IEEE/ACM International Conference On. :1-9 Oct, 2025

Relation: 2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)

Normalization Through Fine-Tuning: Understanding Wav2vec2.0 Embeddings for Phonetic Analysis

Συγγραφείς: Wang, Yiming, Yuan, Jiahong

Πηγή: 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2025 Asia Pacific. :2587-2591 Oct, 2025

Relation: 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

Improving Automatic Speech Recognition Model for Super-Elderly Voice Using Speech Synthesis Model

Συγγραφείς: Uematsu, Ryota, Leow, Chee Siang, Kitaoka, Norihide, Nishizaki, Hiromitsu

Πηγή: 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2025 Asia Pacific. :986-991 Oct, 2025

Relation: 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

Effectiveness of Streaming ASR for Real-Time Laughter and Screaming Detection

Συγγραφείς: Kurasawa, Mizuki, Arimoto, Yoshiko

Πηγή: 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2025 Asia Pacific. :682-687 Oct, 2025

Relation: 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

HIPA-MoE: A Parameter-Efficient Fine-Tuning Architecture with Hierarchical Adapter-Based Mixture-Of-Experts for Multilingual ASR

Συγγραφείς: Lu, Xun, Wang, Xuyang, Cheng, Gaofeng, Zheng, Lin, Zhang, Pengyuan

Πηγή: 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2025 Asia Pacific. :1068-1073 Oct, 2025

Relation: 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

Beyond Binary Detection: Multi-Etiology Dysarthria Classification with Pre-Trained Speech Models

Συγγραφείς: Zhong, Zihan, Wang, Qianli, Singh, Satwinder, Mendes, Clarion, Hasegawa-Johnson, Mark, Abdulla, Waleed, Shahamiri, Seyed Reza

Πηγή: 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2025 Asia Pacific. :706-711 Oct, 2025

Relation: 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

A Robust End to End Spoken Grammar Assessment System

Συγγραφείς: Kopparapu, Sunil Kumar, Bhat, Chitralekha, Panda, Ashish

Πηγή: 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2025 Asia Pacific. :938-943 Oct, 2025

Relation: 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

ASRQ-VC: ASR-Guided Speech Content Quantization for High-Fidelity Voice Conversion

Συγγραφείς: Liu, Songting, Ye, Deheng, Yang, Wei, Li, Haoyang, Chng, Eng Siong

Πηγή: 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2025 Asia Pacific. :741-746 Oct, 2025

Relation: 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

Semi-Supervised End-to-End Speech-to-Text Translation with Joint Text-to-Text and Speech-to-Text Decoding

Συγγραφείς: Tanaka, Tomohiro, Masumura, Ryo, Makishima, Naoki, Ihori, Mana, Orihashi, Shota, Suzuki, Satoshi, Yamane, Taiga

Πηγή: 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2025 Asia Pacific. :909-914 Oct, 2025

Relation: 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

Chain-of-Thought Distillation for ASR Error Correction with Multimodal Large Language Models

Συγγραφείς: Yang, Shaomeng, Luo, Jiaming, Wang, Jinran, Su, Rongfeng, Zhou, Yongjie, Wang, Lan, Yan, Nan

Πηγή: 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2025 Asia Pacific. :777-782 Oct, 2025

Relation: 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

Cross-lingual Transfer Learning Experiments for Arabic ASR

Συγγραφείς: Hassairi, Amin, Mihajlik, Peter

Πηγή: 2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD) Speech Technology and Human-Computer Dialogue (SpeD), 2025 International Conference on. :108-113 Oct, 2025

Relation: 2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)

A Novel Dataset for Testing Anti-spoofing Models in a Telephony Environment

Συγγραφείς: Houghton, Zachary Nicholas, Pluth, Dan, Hosier, Jordan, Gurbani, Vijay K.

Πηγή: 2025 IEEE International Conference and Expo on Real Time Communications at IIT (RTC) Real Time Communications at IIT (RTC), 2025 IEEE International Conference and Expo on. :1-8 Oct, 2025

Relation: 2025 IEEE International Conference and Expo on Real Time Communications at IIT (RTC)

Improved Kazakh Named Entity Transcription Using Synthetic Speech

Συγγραφείς: Meiramov, Rakhat, Varol, Huseyin Atakan

Πηγή: 2025 10th International Conference on Computer Science and Engineering (UBMK) Computer Science and Engineering (UBMK), 2025 10th International Conference on. :1629-1633 Sep, 2025

Relation: 2025 10th International Conference on Computer Science and Engineering (UBMK)