Speech & Audio

A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes Interspeech 2022 A Unified System for Voice Cloning and Voice Conversion through Diffusion Probabilistic Modeling Interspeech 2022 A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network Interspeech 2022 A universally-deployable ASR frontend for joint acoustic echo cancellation, speech enhancement, and voice separation Interspeech 2022 A user-friendly headset for radar-based silent speech recognition Interspeech 2022 Autoencoder-Based Tongue Shape Estimation During Continuous Speech Interspeech 2022 Automated Detection of Wilson’s Disease Based on Improved Mel-frequency Cepstral Coefficients with Signal Decomposition Interspeech 2022 Automated speech tools for helping communities process restricted-access corpora for language revival efforts ACL 2022 Automated Voice Pathology Discrimination from Continuous Speech Benefits from Analysis by Phonetic Context Interspeech 2022 Automatic Detection of Speech Sound Disorder in Child Speech Using Posterior-based Speaker Representations Interspeech 2022 Automatic Evaluation of Speaker Similarity Interspeech 2022 Automatic Learning of Subword Dependent Model Scales Interspeech 2022 Automatic Pronunciation Assessment using Self-Supervised Speech Representation Learning Interspeech 2022 Automatic Prosody Annotation with Pre-Trained Text-Speech Model Interspeech 2022 Automatic Song Translation for Tonal Languages ACL 2022 Automatic Speaker Verification System for Dysarthria Patients Interspeech 2022 Automatic Speech Recognition and Query By Example for Creole Languages Documentation ACL 2022 Autoregressive Co-Training for Learning Discrete Speech Representation Interspeech 2022 AVATAR: Unconstrained Audiovisual Speech Recognition Interspeech 2022 Avoid Overfitting User Specific Information in Federated Keyword Spotting Interspeech 2022 Back to the Future: Extending the Blizzard Challenge 2013 Interspeech 2022 Bayesian Recurrent Units and the Forward-Backward Algorithm Interspeech 2022 ‘Beach’ to ‘Bitch’: Inadvertent Unsafe Transcription of Kids’ Content on YouTube AAAI 2022 Beam-Guided TasNet: An Iterative Speech Separation Framework with Multi-Channel Output Interspeech 2022 BehancePR: A Punctuation Restoration Dataset for Livestreaming Video Transcript NAACL 2022