Have best of both worlds: two-pass hybrid and E2E cascading framework for speech recognition Oct 10, 2021 speech-recognition Speech Recognition
— Unverified Personalized Automatic Speech Recognition Trained on Small Disordered Speech Datasets Oct 9, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Data Augmentation with Locally-time Reversed Speech for Automatic Speech Recognition Oct 9, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Wav2vec-S: Semi-Supervised Pre-Training for Low-Resource ASR Oct 9, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Arabic Speech Emotion Recognition Employing Wav2vec2.0 and HuBERT Based on BAVED Dataset Oct 9, 2021 Deep Learning Emotion Recognition
Code Code Available An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition Oct 9, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified A Genetic Programming Approach To Zero-Shot Neural Architecture Ranking Oct 8, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified SCaLa: Supervised Contrastive Learning for End-to-End Speech Recognition Oct 8, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units Oct 8, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Input Length Matters: Improving RNN-T and MWER Training for Long-form Telephony Speech Recognition Oct 8, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Exploring Heterogeneous Characteristics of Layers in ASR Models for More Efficient Training Oct 8, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Explaining the Attention Mechanism of End-to-End Speech Recognition Using Decision Trees Oct 8, 2021 Decoder speech-recognition
— Unverified Improving Pseudo-label Training For End-to-end Speech Recognition Using Gradient Mask Oct 8, 2021 Pseudo Label Representation Learning
— Unverified Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution Oct 7, 2021 speech-recognition Speech Recognition
— Unverified Back from the future: bidirectional CTC decoding using future information in speech recognition Oct 7, 2021 Language Modeling Language Modelling
— Unverified Analyzing the Robustness of Unsupervised Speech Recognition Oct 7, 2021 Generative Adversarial Network speech-recognition
— Unverified WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition Oct 7, 2021 Label Error Detection Optical Character Recognition
Code Code Available Knowledge Distillation for Neural Transducers from Large Self-Supervised Pre-trained Models Oct 7, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Mandarin-English Code-switching Speech Recognition with Self-supervised Speech Representation Models Oct 7, 2021 Language Identification Self-Supervised Learning
— Unverified Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0 Oct 7, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition Oct 7, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Accent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddings Oct 7, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified FAST-RIR: Fast neural diffuse room impulse response generator Oct 7, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Transcribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers using End-to-End Speaker-Attributed ASR Oct 7, 2021 Action Detection Activity Detection
— Unverified Enabling On-Device Training of Speech Recognition Models with Federated Dropout Oct 7, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognition Oct 6, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified CTC Variations Through New WFST Topologies Oct 6, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Integrating Categorical Features in End-to-End ASR Oct 6, 2021 speech-recognition Speech Recognition
— Unverified Spell my name: keyword boosted speech recognition Oct 6, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Parallel Composition of Weighted Finite-State Transducers Oct 6, 2021 CPU speech-recognition
— Unverified Is Attention always needed? A Case Study on Language Identification from Speech Oct 5, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Late reverberation suppression using U-nets Oct 5, 2021 Decoder Speech Dereverberation
Code Code Available BERT Attends the Conversation: Improving Low-Resource Conversational ASR Oct 5, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition Oct 5, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified ASR Rescoring and Confidence Estimation with ELECTRA Oct 5, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Towards efficient end-to-end speech recognition with biologically-inspired neural networks Oct 4, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Exploiting Pre-Trained ASR Models for Alzheimer's Disease Recognition Through Spontaneous Speech Oct 4, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Building a Noisy Audio Dataset to Evaluate Machine Learning Approaches for Automatic Speech Recognition Systems Oct 4, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Multi-task Voice Activated Framework using Self-supervised Learning Oct 3, 2021 Emotion Classification Keyword Spotting
— Unverified Significance of Data Augmentation for Improving Cleft Lip and Palate Speech Recognition Oct 2, 2021 Data Augmentation speech-recognition
— Unverified Data centric approach to Chinese Medical Speech Recognition Oct 1, 2021 Data Augmentation speech-recognition
— Unverified Chinese Medical Speech Recognition with Punctuated Hypothesis Oct 1, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Exploring the Integration of E2E ASR and Pronunciation Modeling for English Mispronunciation Detection Oct 1, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Exploiting Low-Resource Code-Switching Data to Mandarin-English Speech Recognition Systems Oct 1, 2021 Language Modeling Language Modelling
— Unverified Employing low-pass filtered temporal speech features for the training of ideal ratio mask in speech enhancement Oct 1, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Incremental Layer-wise Self-Supervised Learning for Efficient Speech Domain Adaptation On Device Oct 1, 2021 Domain Adaptation Self-Supervised Learning
— Unverified Speech Technology for Everyone: Automatic Speech Recognition for Non-Native English with Transfer Learning Oct 1, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Improving Punctuation Restoration for Speech Transcripts via External Data Oct 1, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified SpliceOut: A Simple and Efficient Audio Augmentation Method Sep 30, 2021 Audio Classification Automatic Speech Recognition
— Unverified Federated Learning in ASR: Not as Easy as You Think Sep 30, 2021 Federated Learning speech-recognition
Code Code Available 