Improved Speech Pre-Training with Supervision-Enhanced Acoustic Unit Dec 7, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Improved Self-Supervised Multilingual Speech Representation Learning Combined with Auxiliary Language Information Dec 7, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers Dec 7, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Progressive Multi-Scale Self-Supervised Learning for Speech Recognition Dec 7, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Robust Speech Recognition via Large-Scale Weak Supervision Dec 6, 2022 Robust Speech Recognition speech-recognition
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 LMEC: Learnable Multiplicative Absolute Position Embedding Based Conformer for Speech Recognition Dec 5, 2022 Position speech-recognition
Code Code Available Fast and accurate factorized neural transducer for text adaption of end-to-end speech recognition models Dec 5, 2022 Language Modeling Language Modelling
— Unverified Unsupervised Fine-Tuning Data Selection for ASR Using Self-Supervised Speech Models Dec 3, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Continual Learning for On-Device Speech Recognition using Disentangled Conformers Dec 2, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Fuse and Adapt: Investigating the Use of Pre-Trained Self-Supervising Learning Models in Limited Data NLU problems Dec 2, 2022 Domain Adaptation Emotion Recognition
— Unverified Cross-Modal Mutual Learning for Cued Speech Recognition Dec 2, 2022 speech-recognition Speech Recognition
— Unverified SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognition Dec 2, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Surrogate Gradient Spiking Neural Networks as Encoders for Large Vocabulary Continuous Speech Recognition Dec 1, 2022 speech-recognition Speech Recognition
— Unverified Gated Recurrent Neural Networks with Weighted Time-Delay Feedback Dec 1, 2022 Activity Recognition Human Activity Recognition
— Unverified Preliminary Study on SSCF-derived Polar Coordinate for ASR Nov 30, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified EURO: ESPnet Unsupervised ASR Open-source Toolkit Nov 30, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified VideoDubber: Machine Translation with Speech-Aware Length Control for Video Dubbing Nov 30, 2022 Machine Translation Sentence
— Unverified MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition Nov 29, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified 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 Neural Transducer Training: Reduced Memory Consumption with Sample-wise Computation Nov 29, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Better Transcription of UK Supreme Court Hearings Nov 29, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Evaluating and reducing the distance between synthetic and real speech distributions Nov 29, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Handling and extracting key entities from customer conversations using Speech recognition and Named Entity recognition Nov 28, 2022 named-entity-recognition Named Entity Recognition
— Unverified Inter-KD: Intermediate Knowledge Distillation for CTC-Based Automatic Speech Recognition Nov 28, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Bidirectional Representations for Low Resource Spoken Language Understanding Nov 24, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Multitask Learning for Low Resource Spoken Language Understanding Nov 24, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Improving Multi-task Learning via Seeking Task-based Flat Regions Nov 24, 2022 Multi-Task Learning speech-recognition
— Unverified Whose Emotion Matters? Speaking Activity Localisation without Prior Knowledge Nov 23, 2022 Active Speaker Detection Automatic Speech Recognition
Code Code Available Device Directedness with Contextual Cues for Spoken Dialog Systems Nov 23, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Mask the Correct Tokens: An Embarrassingly Simple Approach for Error Correction Nov 23, 2022 Decoder Sentence
— Unverified Benchmarking Evaluation Metrics for Code-Switching Automatic Speech Recognition Nov 22, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Complex-Valued Time-Frequency Self-Attention for Speech Dereverberation Nov 22, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified SSCFormer: Push the Limit of Chunk-wise Conformer for Streaming ASR Using Sequentially Sampled Chunks and Chunked Causal Convolution Nov 21, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Towards continually learning new languages Nov 21, 2022 All speech-recognition
— Unverified SpeechNet: Weakly Supervised, End-to-End Speech Recognition at Industrial Scale Nov 21, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning Nov 21, 2022 Audio-Visual Speech Recognition Language Modelling
— Unverified Constructing Effective Machine Learning Models for the Sciences: A Multidisciplinary Perspective Nov 21, 2022 regression speech-recognition
— Unverified Exploring WavLM on Speech Enhancement Nov 18, 2022 Self-Supervised Learning Speech Enhancement
— Unverified 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 Hey ASR System! Why Aren't You More Inclusive? Automatic Speech Recognition Systems' Bias and Proposed Bias Mitigation Techniques. A Literature Review Nov 17, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Unsupervised Model-based speaker adaptation of end-to-end lattice-free MMI model for speech recognition Nov 17, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified MelHuBERT: A simplified HuBERT on Mel spectrograms Nov 17, 2022 Automatic Speech Recognition Self-Supervised Learning
Code Code Available LongFNT: Long-form Speech Recognition with Factorized Neural Transducer Nov 17, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified L2 proficiency assessment using self-supervised speech representations Nov 16, 2022 speech-recognition Speech Recognition
— Unverified Improving Speech Emotion Recognition with Unsupervised Speaking Style Transfer Nov 16, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified On using the UA-Speech and TORGO databases to validate automatic dysarthric speech classification approaches Nov 16, 2022 Action Detection Activity Detection
— Unverified Streaming Joint Speech Recognition and Disfluency Detection Nov 16, 2022 Decoder Language Modelling
Code Code Available Introducing Semantics into Speech Encoders Nov 15, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Improved disentangled speech representations using contrastive learning in factorized hierarchical variational autoencoder Nov 15, 2022 Contrastive Learning Disentanglement
— Unverified 