Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translation Apr 19, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified An Investigation of Monotonic Transducers for Large-Scale Automatic Speech Recognition Apr 19, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Disappeared Command: Spoofing Attack On Automatic Speech Recognition Systems with Sound Masking Apr 19, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Automated speech tools for helping communities process restricted-access corpora for language revival efforts Apr 15, 2022 Action Detection Activity Detection
— Unverified Lombard Effect for Bilingual Speakers in Cantonese and English: importance of spectro-temporal features Apr 14, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes Apr 13, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Study of Indian English Pronunciation Variabilities relative to Received Pronunciation Apr 13, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Self-critical Sequence Training for Automatic Speech Recognition Apr 13, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified HuBERT-EE: Early Exiting HuBERT for Efficient Speech Recognition Apr 13, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available CorrectSpeech: A Fully Automated System for Speech Correction and Accent Reduction Apr 12, 2022 speech-recognition Speech Recognition
— Unverified ASR in German: A Detailed Error Analysis Apr 12, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Multistream neural architectures for cued-speech recognition using a pre-trained visual feature extractor and constrained CTC decoding Apr 11, 2022 Decoder Lipreading
— Unverified Large-Scale Streaming End-to-End Speech Translation with Neural Transducers Apr 11, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Unified Speech-Text Pre-training for Speech Translation and Recognition Apr 11, 2022 Decoder speech-recognition
— Unverified Building an ASR Error Robust Spoken Virtual Patient System in a Highly Class-Imbalanced Scenario Without Speech Data Apr 11, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Deep Embeddings for Robust User-Based Amateur Vocal Percussion Classification Apr 10, 2022 Classification feature selection
— Unverified Unsupervised Uncertainty Measures of Automatic Speech Recognition for Non-intrusive Speech Intelligibility Prediction Apr 8, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Auditory-Based Data Augmentation for End-to-End Automatic Speech Recognition Apr 8, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Exploiting Hidden Representations from a DNN-based Speech Recogniser for Speech Intelligibility Prediction in Hearing-impaired Listeners Apr 8, 2022 Prediction Speech Enhancement
Code Code Available Adding Connectionist Temporal Summarization into Conformer to Improve Its Decoder Efficiency For Speech Recognition Apr 8, 2022 Decoder speech-recognition
— Unverified Defense against Adversarial Attacks on Hybrid Speech Recognition using Joint Adversarial Fine-tuning with Denoiser Apr 8, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognition Apr 8, 2022 speech-recognition Speech Recognition
Code Code Available Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition Apr 8, 2022 Action Detection Activity Detection
— Unverified Detecting Dysfluencies in Stuttering Therapy Using wav2vec 2.0 Apr 7, 2022 Multi-Task Learning speech-recognition
— Unverified Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-trained DNN-HMM-Based Acoustic-Phonetic Model Apr 7, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified MAESTRO: Matched Speech Text Representations through Modality Matching Apr 7, 2022 Language Modelling Self-Supervised Learning
— Unverified 3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition Apr 7, 2022 Mixture-of-Experts speech-recognition
Code Code Available Enabling All In-Edge Deep Learning: A Literature Review Apr 7, 2022 All Deep Learning
— Unverified A Wav2vec2-Based Experimental Study on Self-Supervised Learning Methods to Improve Child Speech Recognition Apr 6, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Successes and critical failures of neural networks in capturing human-like speech recognition Apr 6, 2022 speech-recognition Speech Recognition
— Unverified Emotional Speech Recognition with Pre-trained Deep Visual Models Apr 6, 2022 Emotion Recognition speech-recognition
Code Code Available Simple and Effective Unsupervised Speech Synthesis Apr 6, 2022 speech-recognition Speech Recognition
— Unverified A survey on recently proposed activation functions for Deep Learning Apr 6, 2022 Deep Learning speech-recognition
— Unverified Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation Apr 6, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified A Complementary Joint Training Approach Using Unpaired Speech and Text for Low-Resource Automatic Speech Recognition Apr 5, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Unsupervised Data Selection via Discrete Speech Representation for ASR Apr 5, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised Objective Apr 5, 2022 Disentanglement Representation Learning
— Unverified Audio-visual multi-channel speech separation, dereverberation and recognition Apr 5, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation Apr 5, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Towards End-to-end Unsupervised Speech Recognition Apr 5, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Low-Latency Speech Separation Guided Diarization for Telephone Conversations Apr 5, 2022 Action Detection Activity Detection
Code Code Available Hear No Evil: Towards Adversarial Robustness of Automatic Speech Recognition via Multi-Task Learning Apr 5, 2022 Adversarial Attack Adversarial Robustness
— Unverified Deliberation Model for On-Device Spoken Language Understanding Apr 4, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified An Analysis of Semantically-Aligned Speech-Text Embeddings Apr 4, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Cross-lingual Self-Supervised Speech Representations for Improved Dysarthric Speech Recognition Apr 4, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems Apr 4, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Self-Supervised Speech Representations Preserve Speech Characteristics while Anonymizing Voices Apr 4, 2022 Speaker Verification speech-recognition
— Unverified Deep Speech Based End-to-End Automated Speech Recognition (ASR) for Indian-English Accents Apr 3, 2022 speech-recognition Speech Recognition
— Unverified Speaker adaptation for Wav2vec2 based dysarthric ASR Apr 2, 2022 speech-recognition Speech Recognition
— Unverified Fast Real-time Personalized Speech Enhancement: End-to-End Enhancement Network (E3Net) and Knowledge Distillation Apr 2, 2022 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified 