ICASSP 2022 Acoustic Echo Cancellation Challenge Feb 27, 2022 Acoustic echo cancellation Speech Enhancement
Code Code Available Integrating Text Inputs For Training and Adapting RNN Transducer ASR Models Feb 26, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Visual Speech Recognition for Multiple Languages in the Wild Feb 26, 2022 Hyperparameter Optimization Lipreading
Code Code Available A Survey of Multilingual Models for Automatic Speech Recognition Feb 25, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Language technology practitioners as language managers: arbitrating data bias and predictive bias in ASR Feb 25, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition Feb 24, 2022 Audio-Visual Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Ask2Mask: Guided Data Selection for Masked Speech Modeling Feb 24, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Towards Better Meta-Initialization with Task Augmentation for Kindergarten-aged Speech Recognition Feb 24, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Closing the Gap between Single-User and Multi-User VoiceFilter-Lite Feb 24, 2022 Speaker Verification speech-recognition
— Unverified Differentially Private Speaker Anonymization Feb 23, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Korean Tokenization for Beam Search Rescoring in Speech Recognition Feb 22, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Improving CTC-based speech recognition via knowledge transferring from pre-trained language models Feb 22, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available VADOI:Voice-Activity-Detection Overlapping Inference For End-to-end Long-form Speech Recognition Feb 22, 2022 Action Detection Activity Detection
— Unverified FlowSense: Monitoring Airflow in Building Ventilation Systems Using Audio Sensing Feb 22, 2022 Privacy Preserving speech-recognition
Code Code Available Adversarial Attacks on Speech Recognition Systems for Mission-Critical Applications: A Survey Feb 22, 2022 Adversarial Attack BIG-bench Machine Learning
— Unverified Spanish and English Phoneme Recognition by Training on Simulated Classroom Audio Recordings of Collaborative Learning Environments Feb 21, 2022 Data Augmentation Phoneme Recognition
Code Code Available r-G2P: Evaluating and Enhancing Robustness of Grapheme to Phoneme Conversion by Controlled noise introducing and Contextual information incorporation Feb 21, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified The PCG-AIID System for L3DAS22 Challenge: MIMO and MISO convolutional recurrent Network for Multi Channel Speech Enhancement and Speech Recognition Feb 21, 2022 Denoising Speech Denoising
— Unverified Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition Feb 21, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified SemEval 2022 Task 12: Symlink- Linking Mathematical Symbols to their Descriptions Feb 19, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Domain Adaptation of low-resource Target-Domain models using well-trained ASR Conformer Models Feb 18, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified End-to-end contextual asr based on posterior distribution adaptation for hybrid ctc/attention system Feb 18, 2022 Decoder speech-recognition
— Unverified 'Beach' to 'Bitch': Inadvertent Unsafe Transcription of Kids' Content on YouTube Feb 17, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Mitigating Closed-model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognition Feb 17, 2022 Adversarial Robustness Automatic Speech Recognition
— Unverified MLP-ASR: Sequence-length agnostic all-MLP architectures for speech recognition Feb 17, 2022 All Automatic Speech Recognition
— Unverified Curriculum optimization for low-resource speech recognition Feb 17, 2022 speech-recognition Speech Recognition
— Unverified AISHELL-NER: Named Entity Recognition from Chinese Speech Feb 17, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Conversational Speech Recognition By Learning Conversation-level Characteristics Feb 16, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Knowledge Transfer from Large-scale Pretrained Language Models to End-to-end Speech Recognizers Feb 16, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified ADIMA: Abuse Detection In Multilingual Audio Feb 16, 2022 Abuse Detection Automatic Speech Recognition
Code Code Available Multi-style Training for South African Call Centre Audio Feb 15, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Learning Contextually Fused Audio-visual Representations for Audio-visual Speech Recognition Feb 15, 2022 Audio-Visual Speech Recognition Lipreading
— Unverified Vau da muntanialas: Energy-efficient multi-die scalable acceleration of RNN inference Feb 14, 2022 Quantization speech-recognition
— Unverified Saving RNN Computations with a Neuron-Level Fuzzy Memoization Scheme Feb 14, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Multimodal Depression Classification Using Articulatory Coordination Features And Hierarchical Attention Based Text Embeddings Feb 13, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified USTED: Improving ASR with a Unified Speech and Text Encoder-Decoder Feb 12, 2022 Decoder Language Modeling
— Unverified Ultra-low Power Always-on Intelligent and Connected SNN-based System for Multimedia IoT-enabled Applications Feb 10, 2022 speech-recognition Speech Recognition
— Unverified Improving Automatic Speech Recognition for Non-Native English with Transfer Learning and Language Model Decoding Feb 10, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available The Volcspeech system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge Feb 9, 2022 Data Augmentation Language Modelling
— Unverified Enhancing ASR for Stuttered Speech with Limited Data Using Detect and Pass Feb 8, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified A two-step approach to leverage contextual data: speech recognition in air-traffic communications Feb 8, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Efficient Adapter Transfer of Self-Supervised Speech Models for Automatic Speech Recognition Feb 7, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available T-NGA: Temporal Network Grafting Algorithm for Learning to Process Spiking Audio Sensor Events Feb 7, 2022 speech-recognition Speech Recognition
— Unverified data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language Feb 7, 2022 image-classification Image Classification
Code Code Available The CUHK-TENCENT speaker diarization system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge Feb 4, 2022 Action Detection Activity Detection
— Unverified Polyphonic pitch detection with convolutional recurrent neural networks Feb 4, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Joint Speech Recognition and Audio Captioning Feb 3, 2022 AudioCaps Audio captioning
— Unverified The RoyalFlush System of Speech Recognition for M2MeT Challenge Feb 3, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Self-supervised Learning with Random-projection Quantizer for Speech Recognition Feb 3, 2022 Self-Supervised Learning speech-recognition
Code Code Available Streaming Multi-Talker ASR with Token-Level Serialized Output Training Feb 2, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available 