COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning Nov 3, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Server-side Rescoring of Spoken Entity-centric Knowledge Queries for Virtual Assistants Nov 2, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Multilingual DistilWhisper: Efficient Distillation of Multi-task Speech Models via Language-Specific Experts Nov 2, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Automatic Disfluency Detection from Untranscribed Speech Nov 1, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling Nov 1, 2023 Hallucination Knowledge Distillation
Code Code Available End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation Nov 1, 2023 Automatic Speech Recognition speech-recognition
Code Code Available RIR-SF: Room Impulse Response Based Spatial Feature for Target Speech Recognition in Multi-Channel Multi-Speaker Scenarios Oct 31, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Combining Language Models For Specialized Domains: A Colorful Approach Oct 30, 2023 Automatic Speech Recognition speech-recognition
— Unverified MUST: A Multilingual Student-Teacher Learning approach for low-resource speech recognition Oct 29, 2023 Knowledge Distillation speech-recognition
— Unverified MixRep: Hidden Representation Mixup for Low-Resource Speech Recognition Oct 27, 2023 Data Augmentation speech-recognition
Code Code Available TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch Oct 27, 2023 Self-Supervised Learning Speech Enhancement
Code Code Available Developing a Multilingual Dataset and Evaluation Metrics for Code-Switching: A Focus on Hong Kong's Polylingual Dynamics Oct 27, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Unified Segment-to-Segment Framework for Simultaneous Sequence Generation Oct 27, 2023 Machine Translation Multi-Task Learning
— Unverified Dialect Adaptation and Data Augmentation for Low-Resource ASR: TalTech Systems for the MADASR 2023 Challenge Oct 26, 2023 Automatic Speech Recognition Data Augmentation
— Unverified UniX-Encoder: A Universal X-Channel Speech Encoder for Ad-Hoc Microphone Array Speech Processing Oct 25, 2023 speaker-diarization Speaker Diarization
— Unverified DISCO: A Large Scale Human Annotated Corpus for Disfluency Correction in Indo-European Languages Oct 25, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available CL-MASR: A Continual Learning Benchmark for Multilingual ASR Oct 25, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Back Transcription as a Method for Evaluating Robustness of Natural Language Understanding Models to Speech Recognition Errors Oct 25, 2023 en-US domain classification en-US Intent Classification
Code Code Available ArTST: Arabic Text and Speech Transformer Oct 25, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available How Much Context Does My Attention-Based ASR System Need? Oct 24, 2023 speech-recognition Speech Recognition
Code Code Available Accented Speech Recognition With Accent-specific Codebooks Oct 24, 2023 Accented Speech Recognition Automatic Speech Recognition
Code Code Available Modality Dropout for Multimodal Device Directed Speech Detection using Verbal and Non-Verbal Features Oct 23, 2023 Automatic Speech Recognition Binary Classification
— Unverified Key Frame Mechanism For Efficient Conformer Based End-to-end Speech Recognition Oct 23, 2023 Automatic Speech Recognition speech-recognition
Code Code Available Quantifying the Dialect Gap and its Correlates Across Languages Oct 23, 2023 Automatic Speech Recognition Machine Translation
— Unverified Leveraging Timestamp Information for Serialized Joint Streaming Recognition and Translation Oct 23, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Delayed Memory Unit: Modelling Temporal Dependency Through Delay Gate Oct 23, 2023 Computational Efficiency Gesture Recognition
Code Code Available Conversational Speech Recognition by Learning Audio-textual Cross-modal Contextual Representation Oct 22, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Intelligibility prediction with a pretrained noise-robust automatic speech recognition model Oct 20, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified SALMONN: Towards Generic Hearing Abilities for Large Language Models Oct 20, 2023 Audio captioning Automatic Speech Recognition
Code Code Available The CHiME-7 Challenge: System Description and Performance of NeMo Team's DASR System Oct 18, 2023 Automatic Speech Recognition speaker-diarization
— Unverified Unintended Memorization in Large ASR Models, and How to Mitigate It Oct 18, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Audio-AdapterFusion: A Task-ID-free Approach for Efficient and Non-Destructive Multi-task Speech Recognition Oct 17, 2023 speech-recognition Speech Recognition
— Unverified Generative error correction for code-switching speech recognition using large language models Oct 17, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Iterative Shallow Fusion of Backward Language Model for End-to-End Speech Recognition Oct 17, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Multi-stage Large Language Model Correction for Speech Recognition Oct 17, 2023 Language Modeling Language Modelling
— Unverified Advanced accent/dialect identification and accentedness assessment with multi-embedding models and automatic speech recognition Oct 17, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Correction Focused Language Model Training for Speech Recognition Oct 17, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Zipformer: A faster and better encoder for automatic speech recognition Oct 17, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Long-form Simultaneous Speech Translation: Thesis Proposal Oct 17, 2023 Form Machine Translation
— Unverified VoxArabica: A Robust Dialect-Aware Arabic Speech Recognition System Oct 17, 2023 Arabic Speech Recognition Automatic Speech Recognition
— Unverified Detecting Speech Abnormalities with a Perceiver-based Sequence Classifier that Leverages a Universal Speech Model Oct 16, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Personalization of CTC-based End-to-End Speech Recognition Using Pronunciation-Driven Subword Tokenization Oct 16, 2023 Automatic Speech Recognition speech-recognition
— Unverified Optimized Tokenization for Transcribed Error Correction Oct 16, 2023 speech-recognition Speech Recognition
— Unverified End-to-end Multichannel Speaker-Attributed ASR: Speaker Guided Decoder and Input Feature Analysis Oct 16, 2023 Automatic Speech Recognition Decoder
— Unverified Large Vocabulary Spontaneous Speech Recognition for Tigrigna Oct 15, 2023 Automatic Speech Recognition Language Modeling
— Unverified Homophone Disambiguation Reveals Patterns of Context Mixing in Speech Transformers Oct 15, 2023 Decoder speech-recognition
Code Code Available Advancing Test-Time Adaptation in Wild Acoustic Test Settings Oct 14, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
Code Code Available Improved Contextual Recognition In Automatic Speech Recognition Systems By Semantic Lattice Rescoring Oct 14, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation Oct 13, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified Fast Word Error Rate Estimation Using Self-Supervised Representations for Speech and Text Oct 12, 2023 Automatic Speech Recognition Automatic Speech Recognition (ASR)
— Unverified 