One model to enhance them all: array geometry agnostic multi-channel personalized speech enhancement Oct 20, 2021 All Automatic Speech Recognition
— Unverified Knowledge distillation from language model to acoustic model: a hierarchical multi-task learning approach Oct 20, 2021 Knowledge Distillation Language Modeling
— Unverified Progressive Learning for Stabilizing Label Selection in Speech Separation with Mapping-based Method Oct 20, 2021 Speech Recognition Speech Separation
— Unverified An Investigation of Enhancing CTC Model for Triggered Attention-based Streaming ASR Oct 20, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Speech Pattern based Black-box Model Watermarking for Automatic Speech Recognition Oct 19, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified AequeVox: Automated Fairness Testing of Speech Recognition Systems Oct 19, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Personalized Speech Enhancement: New Models and Comprehensive Evaluation Oct 18, 2021 Speech Enhancement speech-recognition
— Unverified Similarity-and-Independence-Aware Beamformer with Iterative Casting and Boost Start for Target Source Extraction Using Reference Oct 18, 2021 Speech Enhancement speech-recognition
— Unverified Automatic Learning of Subword Dependent Model Scales Oct 18, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Analysis of French Phonetic Idiosyncrasies for Accent Recognition Oct 18, 2021 Multi-class Classification speech-recognition
Code Code Available ViraPart: A Text Refinement Framework for Automatic Speech Recognition and Natural Language Processing Tasks in Persian Oct 18, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Intent Classification Using Pre-trained Language Agnostic Embeddings For Low Resource Languages Oct 18, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Efficient Sequence Training of Attention Models using Approximative Recombination Oct 18, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified OkwuGbé: End-to-End Speech Recognition for Fon and Igbo Oct 16, 2021 Machine Translation speech-recognition
— Unverified Towards Robust Waveform-Based Acoustic Models Oct 16, 2021 Data Augmentation Inductive Bias
— Unverified A Unified Speaker Adaptation Approach for ASR Oct 16, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Multilingual Speech Recognition using Knowledge Transfer across Learning Processes Oct 15, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet Oct 15, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Scribosermo: Fast Speech-to-Text models for German and other Languages Oct 15, 2021 Speech Recognition Speech-to-Text
Code Code Available Towards Identity Preserving Normal to Dysarthric Voice Conversion Oct 15, 2021 Data Augmentation Decision Making
— Unverified Advances and Challenges in Deep Lip Reading Oct 15, 2021 Deep Learning Lip Reading
— Unverified CORAA: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese Oct 14, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Sub-word Level Lip Reading With Visual Attention Oct 14, 2021 Audio-Visual Active Speaker Detection Automatic Speech Recognition
— Unverified Identifying Introductions in Podcast Episodes from Automatically Generated Transcripts Oct 14, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing Oct 14, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available All-neural beamformer for continuous speech separation Oct 13, 2021 All Automatic Speech Recognition
— Unverified Continual learning using lattice-free MMI for speech recognition Oct 13, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Prompt-tuning in ASR systems for efficient domain-adaptation Oct 13, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Perception Point: Identifying Critical Learning Periods in Speech for Bilingual Networks Oct 13, 2021 Lip Reading speech-recognition
— Unverified On Language Model Integration for RNN Transducer based Speech Recognition Oct 13, 2021 Language Modeling Language Modelling
— Unverified Multi-Modal Pre-Training for Automated Speech Recognition Oct 12, 2021 Language Modeling Language Modelling
— Unverified UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training Oct 12, 2021 Data Augmentation Multi-Task Learning
Code Code Available Word Order Does Not Matter For Speech Recognition Oct 12, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Improving Character Error Rate Is Not Equal to Having Clean Speech: Speech Enhancement for ASR Systems with Black-box Acoustic Models Oct 12, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Speech Summarization using Restricted Self-Attention Oct 12, 2021 Document Summarization speech-recognition
— Unverified Exploring Wav2vec 2.0 fine-tuning for improved speech emotion recognition Oct 12, 2021 Emotion Recognition Speech Emotion Recognition
Code Code Available LightSeq2: Accelerated Training for Transformer-based Models on GPUs Oct 12, 2021 Decoder GPU
Code Code Available BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications Oct 12, 2021 Action Detection Activity Detection
Code Code Available Partial Variable Training for Efficient On-Device Federated Learning Oct 11, 2021 Federated Learning speech-recognition
— Unverified SRU++: Pioneering Fast Recurrence with Attention for Speech Recognition Oct 11, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition Oct 11, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation Oct 11, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified K-Wav2vec 2.0: Automatic Speech Recognition based on Joint Decoding of Graphemes and Syllables Oct 11, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy Oct 11, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Evaluating User Perception of Speech Recognition System Quality with Semantic Distance Metric Oct 11, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition Oct 11, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Long Expressive Memory for Sequence Modeling Oct 10, 2021 Language Modeling Language Modelling
Code Code Available Towards High-fidelity Singing Voice Conversion with Acoustic Reference and Contrastive Predictive Coding Oct 10, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Have best of both worlds: two-pass hybrid and E2E cascading framework for speech recognition Oct 10, 2021 speech-recognition Speech Recognition
— Unverified DITTO: Data-efficient and Fair Targeted Subset Selection for ASR Accent Adaptation Oct 10, 2021 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified 