#Speech Recognition

Articles (10)

• 🇺🇸 LoASR-Bench: Evaluating Large Speech Language Models on Low-Resource Automatic Speech Recognition Across Language Families — 23/03/2026 [USA]

  arXiv:2603.20042v1 Announce Type: cross Abstract: Large language models (LLMs) have driven substantial advances in speech language models (SpeechLMs), yielding strong performance in automatic speech ...

  Related: #AI Evaluation
• 🇺🇸 Demonstration of Adapt4Me: An Uncertainty-Aware Authoring Environment for Personalizing Automatic Speech Recognition to Non-normative Speech — 23/03/2026 [USA]

  arXiv:2603.20112v1 Announce Type: cross Abstract: Personalizing Automatic Speech Recognition (ASR) for non-normative speech remains challenging because data collection is labor-intensive and model tr...

  Related: #Accessibility Technology
• 🇺🇸 ProKWS: Personalized Keyword Spotting via Collaborative Learning of Phonemes and Prosody — 20/03/2026 [USA]

  arXiv:2603.18024v1 Announce Type: cross Abstract: Current keyword spotting systems primarily use phoneme-level matching to distinguish confusable words but ignore user-specific pronunciation traits l...

  Related: #Personalized AI
• 🇺🇸 SENS-ASR: Semantic Embedding injection in Neural-transducer for Streaming Automatic Speech Recognition — 12/03/2026 [USA]

  arXiv:2603.10005v1 Announce Type: cross Abstract: Many Automatic Speech Recognition (ASR) applications require streaming processing of the audio data. In streaming mode, ASR systems need to start tra...

  Related: #AI Technology
• 🇺🇸 Whisper-CD: Accurate Long-Form Speech Recognition using Multi-Negative Contrastive Decoding — 09/03/2026 [USA]

  arXiv:2603.06193v1 Announce Type: cross Abstract: Long-form speech recognition with large encoder-decoder models such as Whisper often exhibit hallucinations, repetition loops, and content omissions....

  Related: #AI Technology
• 🇺🇸 When Denoising Hinders: Revisiting Zero-Shot ASR with SAM-Audio and Whisper — 06/03/2026 [USA]

  arXiv:2603.04710v1 Announce Type: cross Abstract: Recent advances in automatic speech recognition (ASR) and speech enhancement have led to a widespread assumption that improving perceptual audio qual...

  Related: #Audio Processing
• 🇺🇸 Training-Free Intelligibility-Guided Observation Addition for Noisy ASR — 25/02/2026 [USA]

  arXiv:2602.20967v1 Announce Type: cross Abstract: Automatic speech recognition (ASR) degrades severely in noisy environments. Although speech enhancement (SE) front-ends effectively suppress backgrou...

  Related: #Audio Processing, #Machine Learning, #Noise Reduction
• 🇺🇸 Wispr Flow launches an Android app for AI-powered dictation — 23/02/2026 [USA]

  AI-powered dictation startup Wispr Flow has launched its Android app today. The company released its app for Mac and Windows first, then launched on iOS in June 2025. On iOS, users could use Wispr Flo...

  Related: #AI Technology, #Mobile Applications, #Venture Funding
• 🇺🇸 The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASR$\rightarrow$LLM Pipelines? — 20/02/2026 [USA]

  arXiv:2602.17598v1 Announce Type: cross Abstract: Current speech LLMs largely perform implicit ASR: on tasks solvable from a transcript, they are behaviorally and mechanistically equivalent to simple...

  Related: #Large Language Models, #Model Architecture Comparison, #Audio Processing, #Efficiency and Cost Analysis
• 🇺🇸 SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise — 16/02/2026 [USA]

  arXiv:2602.12783v1 Announce Type: cross Abstract: Spoken query retrieval is an important interaction mode in modern information retrieval. However, existing evaluation datasets are often limited to s...

  Related: #Technology Evaluation, #Information Retrieval