Speech & Audio

Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid TDNN ASR Systems Interspeech 2022 Two-Pass Low Latency End-to-End Spoken Language Understanding Interspeech 2022 u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality NeurIPS 2022 Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translation ACL 2022 UNet-DenseNet for Robust Far-Field Speaker Verification Interspeech 2022 Unified Speech-Text Pre-training for Speech Translation and Recognition ACL 2022 Unifying Cosine and PLDA Back-ends for Speaker Verification Interspeech 2022 Unsupervised Acoustic-to-Articulatory Inversion with Variable Vocal Tract Anatomy Interspeech 2022 Unsupervised Data Selection via Discrete Speech Representation for ASR Interspeech 2022 Unsupervised domain adaptation for speech recognition with unsupervised error correction Interspeech 2022 Unsupervised Instance Discriminative Learning for Depression Detection from Speech Signals Interspeech 2022 Unsupervised Speaker Diarization that is Agnostic to Language, Overlap-Aware, and Tuning Free Interspeech 2022 Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition Interspeech 2022 Unsupervised Training of Sequential Neural Beamformer Using Coarsely-separated and Non-separated Signals Interspeech 2022 Unsupervised Uncertainty Measures of Automatic Speech Recognition for Non-intrusive Speech Intelligibility Prediction Interspeech 2022 Unsupervised Word Segmentation using K Nearest Neighbors Interspeech 2022 Updating Only Encoders Prevents Catastrophic Forgetting of End-to-End ASR Models Interspeech 2022 Use of Nods Less Synchronized with Turn-Taking and Prosody During Conversations in Adults with Autism Interspeech 2022 Use of prosodic and lexical cues for disambiguating wh-words in Korean Interspeech 2022 User-Level Differential Privacy against Attribute Inference Attack of Speech Emotion Recognition on Federated Learning Interspeech 2022 UserLibri: A Dataset for ASR Personalization Using Only Text Interspeech 2022 Using ASR-Generated Text for Spoken Language Modeling ACL 2022 Using BERT Embeddings to Model Word Importance in Conversational Transcripts for Deaf and Hard of Hearing Users ACL 2022 Using cross-model learnings for the Gram Vaani ASR Challenge 2022 Interspeech 2022 Using Data Augmentation and Consistency Regularization to Improve Semi-supervised Speech Recognition Interspeech 2022