STHG: Spatial-Temporal Heterogeneous Graph Learning for Advanced Audio-Visual Diarization Jun 18, 2023 All Graph Learning
Code Code Available Pushing the Limits of Unsupervised Unit Discovery for SSL Speech Representation Jun 15, 2023 Automatic Speech Recognition Clustering
Code Code Available Utilizing Longitudinal Chest X-Rays and Reports to Pre-Fill Radiology Reports Jun 14, 2023 Decoder speech-recognition
Code Code Available ITALIC: An Italian Intent Classification Dataset Jun 14, 2023 Classification intent-classification
Code Code Available Contrastive Learning-Based Audio to Lyrics Alignment for Multiple Languages Jun 13, 2023 Contrastive Learning speech-recognition
Code Code Available OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment Jun 10, 2023 Audio-Visual Speech Recognition Lip Reading
Code Code Available Zambezi Voice: A Multilingual Speech Corpus for Zambian Languages Jun 7, 2023 Cross-Lingual Transfer speech-recognition
Code Code Available Allophant: Cross-lingual Phoneme Recognition with Articulatory Attributes Jun 7, 2023 Attribute Cross-Lingual Transfer
Code Code Available MAVD: The First Open Large-Scale Mandarin Audio-Visual Dataset with Depth Information Jun 4, 2023 Audio-Visual Speech Recognition speech-recognition
Code Code Available SGEM: Test-Time Adaptation for Automatic Speech Recognition via Sequential-Level Generalized Entropy Minimization Jun 3, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Can Contextual Biasing Remain Effective with Whisper and GPT-2? Jun 2, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Improved DeepFake Detection Using Whisper Features Jun 2, 2023 Automatic Speech Recognition DeepFake Detection
Code Code Available DistilXLSR: A Light Weight Cross-Lingual Speech Representation Model Jun 2, 2023 speech-recognition Speech Recognition
Code Code Available Perception and Semantic Aware Regularization for Sequential Confidence Calibration May 31, 2023 Language Modelling speech-recognition
Code Code Available Bridging the Granularity Gap for Acoustic Modeling May 27, 2023 speech-recognition Speech Recognition
Code Code Available BIG-C: a Multimodal Multi-Purpose Dataset for Bemba May 26, 2023 Machine Translation speech-recognition
Code Code Available Scaling Speech Technology to 1,000+ Languages May 22, 2023 Automatic Speech Recognition Language Identification
Code Code Available CopyNE: Better Contextual ASR by Copying Named Entities May 22, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation May 18, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Prompting the Hidden Talent of Web-Scale Speech Models for Zero-Shot Task Generalization May 18, 2023 Audio-Visual Speech Recognition Prompt Engineering
Code Code Available Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering May 18, 2023 Acoustic Unit Discovery Clustering
Code Code Available Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition May 16, 2023 Audio-Visual Speech Recognition Automatic Speech Recognition
Code Code Available Back Translation for Speech-to-text Translation Without Transcripts May 15, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available CB-Conformer: Contextual biasing Conformer for biased word recognition Apr 19, 2023 Automatic Speech Recognition Language Modeling
Code Code Available Efficient Sequence Transduction by Jointly Predicting Tokens and Durations Apr 13, 2023 Intent Classification Intent Classification and Slot Filling
Code Code Available When Good and Reproducible Results are a Giant with Feet of Clay: The Importance of Software Quality in NLP Mar 28, 2023 Automatic Speech Recognition speech-recognition
Code Code Available Watch or Listen: Robust Audio-Visual Speech Recognition with Visual Corruption Modeling and Reliability Scoring Mar 15, 2023 Audio-Visual Speech Recognition speech-recognition
Code Code Available TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings Mar 7, 2023 Action Detection Activity Detection
Code Code Available Calibrating Transformers via Sparse Gaussian Processes Mar 4, 2023 Bayesian Inference Gaussian Processes
Code Code Available BrainBERT: Self-supervised representation learning for intracranial recordings Feb 28, 2023 Language Modeling Language Modelling
Code Code Available Structured Pruning of Self-Supervised Pre-trained Models for Speech Recognition and Understanding Feb 27, 2023 Model Compression Representation Learning
Code Code Available Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognition Feb 22, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available A Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-Talker One Feb 20, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Complex Dynamic Neurons Improved Spiking Transformer Network for Efficient Automatic Speech Recognition Feb 2, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation Jan 30, 2023 Automatic Speech Recognition Knowledge Distillation
Code Code Available OLKAVS: An Open Large-Scale Korean Audio-Visual Speech Dataset Jan 16, 2023 Audio-Visual Speech Recognition Lip Reading
Code Code Available Audio-Visual Efficient Conformer for Robust Speech Recognition Jan 4, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Towards Voice Reconstruction from EEG during Imagined Speech Jan 2, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Learning to Detect Noisy Labels Using Model-Based Features Dec 28, 2022 Meta-Learning speech-recognition
Code Code Available Skit-S2I: An Indian Accented Speech to Intent dataset Dec 26, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language Dec 14, 2022 Decoder image-classification
Code Code Available Jointly Learning Visual and Auditory Speech Representations from Raw Data Dec 12, 2022 Audio-Visual Speech Recognition Lipreading
Code Code Available BASPRO: a balanced script producer for speech corpus collection based on the genetic algorithm Dec 11, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available GPU-accelerated Guided Source Separation for Meeting Transcription Dec 10, 2022 blind source separation CPU
Code Code Available SoftCTC -- Semi-Supervised Learning for Text Recognition using Soft Pseudo-Labels Dec 5, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available On Word Error Rate Definitions and their Efficient Computation for Multi-Speaker Speech Recognition Systems Nov 29, 2022 speech-recognition Speech Recognition
Code Code Available A Persian ASR-based SER: Modification of Sharif Emotional Speech Database and Investigation of Persian Text Corpora Nov 18, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available MelHuBERT: A simplified HuBERT on Mel spectrograms Nov 17, 2022 Automatic Speech Recognition Self-Supervised Learning
Code Code Available MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets Nov 14, 2022 Automatic Speech Recognition Multi-Task Learning
Code Code Available ATCO2 corpus: A Large-Scale Dataset for Research on Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communications Nov 8, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available 