{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"2005.07143","title":"ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification","created":"2020-05-14","cited_by_count":628},{"id":"2111.09296","title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","created":"2021-11-17","cited_by_count":601},{"id":"1508.01211","title":"Listen, Attend and Spell","created":"2015-08-05","cited_by_count":543},{"id":"2205.12446","title":"FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech","created":"2022-05-25","cited_by_count":469},{"id":"2104.09494","title":"NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets","created":"2021-04-19","cited_by_count":192},{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184},{"id":"2406.04904","title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model","created":"2024-06-07","cited_by_count":179},{"id":"2101.01785","title":"ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic","created":"2020-12-27","cited_by_count":166},{"id":"2011.12998","title":"VoxLingua107: a Dataset for Spoken Language Recognition","created":"2020-11-25","cited_by_count":122},{"id":"2409.09305","title":"The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech","created":"2024-09-14","cited_by_count":83},{"id":"2305.18975","title":"Voice Conversion With Just Nearest Neighbors","created":"2023-05-30","cited_by_count":68},{"id":"1709.07276","title":"Speech Recognition Challenge in the Wild: Arabic MGB-3","created":"2017-09-21","cited_by_count":60},{"id":"2010.11334","title":"NADI 2020: The First Nuanced Arabic Dialect Identification Shared Task","created":"2020-10-21","cited_by_count":47},{"id":"2106.13000","title":"QASR: QCRI Aljazeera Speech Resource -- A Large Scale Annotated Arabic Speech Corpus","created":"2021-06-24","cited_by_count":38},{"id":"2103.08466","title":"NADI 2021: The Second Nuanced Arabic Dialect Identification Shared Task","created":"2021-03-04","cited_by_count":32},{"id":"2310.16117","title":"NADI 2023: The Fourth Nuanced Arabic Dialect Identification Shared Task","created":"2023-10-24","cited_by_count":29},{"id":"2210.09582","title":"NADI 2022: The Third Nuanced Arabic Dialect Identification Shared Task","created":"2022-10-18","cited_by_count":23},{"id":"2407.04910","title":"NADI 2024: The Fifth Nuanced Arabic Dialect Identification Shared Task","created":"2024-07-06","cited_by_count":23},{"id":"1609.05625","title":"The MGB-2 Challenge: Arabic Multi-Dialect Broadcast Media Recognition","created":"2016-09-19","cited_by_count":22},{"id":"2408.03900","title":"Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond","created":"2024-08-07","cited_by_count":20},{"id":"2410.04527","title":"Casablanca: Data and Models for Multidialectal Arabic Speech Recognition","created":"2024-10-06","cited_by_count":20},{"id":"2409.20201","title":"AfriHuBERT: A self-supervised speech representation model for African languages","created":"2024-09-30","cited_by_count":18},{"id":"2310.16621","title":"ArTST: Arabic Text and Speech Transformer","created":"2023-10-25","cited_by_count":14},{"id":"2211.12000","title":"ArzEn-ST: A Three-way Speech Translation Corpus for Code-Switched Egyptian Arabic - English","created":"2022-11-22","cited_by_count":13},{"id":"2306.03789","title":"On the Robustness of Arabic Speech Dialect Identification","created":"2023-06-01","cited_by_count":13},{"id":"2505.19179","title":"BR-ASR: Efficient and Scalable Bias Retrieval Framework for Contextual Biasing ASR in Speech LLM","created":"2025-05-25","cited_by_count":11},{"id":"2506.19398","title":"ClearerVoice-Studio: Bridging Advanced Speech Processing Research and Practical Deployment","created":"2025-06-24","cited_by_count":11},{"id":"2407.04533","title":"Performance Analysis of Speech Encoders for Low-Resource SLU and ASR in Tunisian Dialect","created":"2024-07-05","cited_by_count":7},{"id":"2506.02627","title":"Overcoming Data Scarcity in Multi-Dialectal Arabic ASR via Whisper Fine-Tuning","created":"2025-06-03","cited_by_count":7},{"id":"2506.02894","title":"A Multi-Dialectal Dataset for German Dialect ASR and Dialect-to-Standard Speech Translation","created":"2025-06-03","cited_by_count":7},{"id":"2506.11089","title":"Better Pseudo-labeling with Multi-ASR Fusion and Error Correction by SpeechLLM","created":"2025-06-05","cited_by_count":6},{"id":"2506.16558","title":"Automatic Speech Recognition Biases in Newcastle English: an Error Analysis","created":"2025-06-19","cited_by_count":6},{"id":"2509.12093","title":"SENSE models: an open source solution for multilingual and multimodal semantic-based tasks","created":"2025-09-15","cited_by_count":6},{"id":"1709.00387","title":"MIT-QCRI Arabic Dialect Identification System for the 2017 Multi-Genre Broadcast Challenge","created":"2017-08-28","cited_by_count":5},{"id":"2505.21138","title":"Leveraging LLM and Self-Supervised Training Models for Speech Recognition in Chinese Dialects: A Comparative Analysis","created":"2025-05-27","cited_by_count":5},{"id":"2506.04915","title":"A Practitioner's Guide to Building ASR Models for Low-Resource Languages: A Case Study on Scottish Gaelic","created":"2025-06-05","cited_by_count":5},{"id":"2506.21576","title":"Adapting Whisper for Parameter-efficient Code-Switching Speech Recognition via Soft Prompt Tuning","created":"2025-06-16","cited_by_count":5},{"id":"2607.23938","title":"Qwen-Audio-3.0-TTS: Freely Controllable and Highly Robust Speech Synthesis with Multi-Stage Training Paradigm","created":"2026-07-27","cited_by_count":5},{"id":"2302.05110","title":"Cross-Corpora Spoken Language Identification with Domain Diversification and Generalization","created":"2023-02-10","cited_by_count":4},{"id":"2601.13319","title":"Arab Voices: Mapping Standard and Dialectal Arabic Speech Technology","created":"2026-01-19","cited_by_count":4},{"id":"2505.21527","title":"VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining","created":"2025-05-23","cited_by_count":3},{"id":"2511.10070","title":"ADI-20: Arabic Dialect Identification dataset and models","created":"2025-11-13","cited_by_count":3},{"id":"2511.10780","title":"TEDxTN: A Three-way Speech Translation Corpus for Code-Switched Tunisian Arabic - English","created":"2025-11-13","cited_by_count":3},{"id":"2506.06888","title":"Automatic Speech Recognition of African American English: Lexical and Contextual Effects","created":"2025-06-07","cited_by_count":2},{"id":"2603.21900","title":"Ara-Best-RQ: Multi Dialectal Arabic SSL","created":"2026-03-23","cited_by_count":2},{"id":"2511.10090","title":"ELYADATA & LIA at NADI 2025: ASR and ADI Subtasks","created":"2025-11-13","cited_by_count":1},{"id":"2602.15675","title":"LLM-to-Speech: A Synthetic Data Pipeline for Training Dialectal Text-to-Speech Models","created":"2026-02-17","cited_by_count":1},{"id":"2608.18689","title":"Aslema at NADI 2026: Data Augmentation for Intent Recognition and Slot Filling","created":"2026-08-19","cited_by_count":1},{"id":"2608.21950","title":"Bulbul: A Dataset for Dialectal Arabic Speech Recognition","created":"2026-08-22","cited_by_count":1}],"next_cursor":null}