Showing 1–20 of 27 results
/ Date/ Name
Aug 8, 2020Exploring the Use of an Unsupervised Autoregressive Model as a Shared Encoder for Text-Dependent Speaker VerificationApr 15, 2023A CTC Alignment-based Non-autoregressive Transformer for End-to-end Automatic Speech RecognitionOct 16, 2022Acoustic-aware Non-autoregressive Spell Correction with Mask Sample DecodingJun 18, 2021An Improved Single Step Non-autoregressive Transformer for Automatic Speech RecognitionDec 2, 2024AlignFormer: Modality Matching Can Achieve Better Zero-shot Instruction-Following Speech-LLMJun 16, 2022DRAFT: A Novel Framework to Reduce Domain Shifting in Self-supervised Learning and Its Application to Children's ASRApr 28, 2023Towards Better Domain Adaptation for Self-supervised Models: A Case Study of Child ASRJun 15, 2024Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation ModelsOct 28, 2020CASS-NAT: CTC Alignment-based Single Step Non-autoregressive Transformer for Speech RecognitionJun 15, 2024SOA: Reducing Domain Mismatch in SSL Pipeline by Speech Only Adaptation for Low Resource ASRFeb 14, 2024UniEnc-CASSNAT: An Encoder-only Non-autoregressive ASR for Speech SSL ModelsOct 16, 2022CTCBERT: Advancing Hidden-unit BERT with CTC ObjectivesFeb 12, 2021Bi-APC: Bidirectional Autoregressive Predictive Coding for Unsupervised Pre-training and Its Application to Children's ASRSep 4, 2025OleSpeech-IV: A Large-Scale Multispeaker and Multilingual Conversational Speech Dataset with Diverse TopicsNov 20, 2025Train Short, Infer Long: Speech-LLM Enables Zero-Shot Streamable Joint ASR and Diarization on Long AudioJun 4, 2025Towards Efficient Speech-Text Jointly Decoding within One Speech Language ModelOct 7, 2024CTC-GMM: CTC guided modality matching for fast and accurate streaming speech translationJun 4, 2025SLM-S2ST: A multimodal language model for direct speech-to-speech translationNov 13, 2018An Online Attention-based Model for Speech RecognitionJun 18, 2021Low Resource German ASR with Untranscribed Data Spoken by Non-native Children -- INTERSPEECH 2021 Shared Task SPAPL System