Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding Apr 13, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept Apr 13, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified EAT: Enhanced ASR-TTS for Self-supervised Speech Recognition Apr 13, 2021 Language Modeling Language Modelling
Code Code Available Experiments of ASR-based mispronunciation detection for children and adult English learners Apr 13, 2021 Language Modelling speech-recognition
— Unverified Source and Target Bidirectional Knowledge Distillation for End-to-end Speech Translation Apr 13, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Improved Conformer-based End-to-End Speech Recognition Using Neural Architecture Search Apr 12, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures Apr 12, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified NeMo Inverse Text Normalization: From Development To Production Apr 11, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Innovative Bert-based Reranking Language Models for Speech Recognition Apr 11, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Non-autoregressive Transformer-based End-to-end ASR using BERT Apr 10, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified On Architectures and Training for Raw Waveform Feature Extraction in ASR Apr 9, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Accented Speech Recognition Inspired by Human Perception Apr 9, 2021 Accented Speech Recognition Automatic Speech Recognition
— Unverified Language model fusion for streaming end to end speech recognition Apr 9, 2021 Language Modeling Language Modelling
— Unverified Lookup-Table Recurrent Language Models for Long Tail Speech Recognition Apr 9, 2021 GPU Language Modeling
— Unverified The NTNU Taiwanese ASR System for Formosa Speech Recognition Challenge 2020 Apr 9, 2021 Data Augmentation Speech Enhancement
— Unverified WNARS: WFST based Non-autoregressive Streaming End-to-End Speech Recognition Apr 8, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified BSTC: A Large-Scale Chinese-English Speech Translation Dataset Apr 8, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Layer Reduction: Accelerating Conformer-Based Self-Supervised Model via Layer Consistency Apr 8, 2021 speech-recognition Speech Recognition
— Unverified Contextual Semi-Supervised Learning: An Approach To Leverage Air-Surveillance and Untranscribed ATC Data in ASR Systems Apr 8, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Exploring Machine Speech Chain for Domain Adaptation and Few-Shot Speaker Adaptation Apr 8, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization Apr 7, 2021 Decoder Position
— Unverified Pushing the Limits of Non-Autoregressive Speech Recognition Apr 7, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Capturing Multi-Resolution Context by Dilated Self-Attention Apr 7, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Optimal Transport-based Adaptation in Dysarthric Speech Tasks Apr 6, 2021 speech-recognition Speech Recognition
— Unverified Dissecting User-Perceived Latency of On-Device E2E Speech Recognition Apr 6, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified AI4D -- African Language Program Apr 6, 2021 Machine Translation speech-recognition
Code Code Available Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions Apr 6, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarios Apr 6, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified LT-LM: a novel non-autoregressive language model for single-shot lattice rescoring Apr 6, 2021 ARC Automatic Speech Recognition
Code Code Available Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Models Apr 6, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Non-autoregressive Mandarin-English Code-switching Speech Recognition Apr 6, 2021 Decoder Sentence
— Unverified Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0 acoustic model Apr 6, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding Apr 5, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified End-to-End Speaker-Attributed ASR with Transformer Apr 5, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Streaming Multi-talker Speech Recognition with Joint Speaker Identification Apr 5, 2021 Speaker Identification speech-recognition
— Unverified Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency Apr 5, 2021 speech-recognition Speech Recognition
— Unverified SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition Apr 5, 2021 speech-recognition Speech Recognition
Code Code Available Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition Apr 5, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Speaker conditioned acoustic modeling for multi-speaker conversational ASR Apr 5, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Talk, Don't Write: A Study of Direct Speech-Based Image Retrieval Apr 5, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network Apr 5, 2021 All Language Modeling
— Unverified Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion Apr 5, 2021 Language Modeling Language Modelling
— Unverified Towards Lifelong Learning of End-to-end ASR Apr 4, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified TransfoRNN: Capturing the Sequential Information in Self-Attention Representations for Language Modeling Apr 4, 2021 Language Modeling Language Modelling
— Unverified Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties Apr 4, 2021 Phoneme Recognition speech-recognition
— Unverified TSNAT: Two-Step Non-Autoregressvie Transformer Models for Speech Recognition Apr 4, 2021 Decoder speech-recognition
Code Code Available On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASR Apr 3, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Adversarial Joint Training with Self-Attention Mechanism for Robust End-to-End Speech Recognition Apr 3, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified HMM-Free Encoder Pre-Training for Streaming RNN Transducer Apr 2, 2021 Speech Recognition
— Unverified Disfluency Correction using Unsupervised and Semi-supervised Learning Apr 1, 2021 Decoder speech-recognition
— Unverified 