Speech translation
PulseAugur coverage of Speech translation — every cluster mentioning Speech translation across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New method EA-SURF optimizes multi-task speech LLMs
Researchers have developed a new method called EA-SURF (Endpoint-Anchored Preference-Aware Sampling Uniformly along the Pareto Front) to better manage task trade-offs in multi-task speech large language models. This app…
-
New method EA-SURF optimizes speech LLM task trade-offs
Researchers have developed a new method called EA-SURF to address task trade-offs in speech large language models (LLMs). These models often perform multiple tasks like speech recognition, timestamp prediction, and spee…
-
New LPR method enhances Speech-to-LLM bridge pretraining
Researchers have developed a new pretraining method called Local Prototype Reconstruction (LPR) to improve the performance of Speech-to-LLM systems. LPR focuses on ensuring that the bridge between speech and language mo…
-
New method synthesizes pseudo-dialect speech to boost SLM performance
Researchers have developed a novel method to improve the performance of Speech Language Models (SLMs) on various dialects by synthesizing pseudo-dialect speech. This technique converts text from dialects into speech usi…
-
New frameworks enhance LLMs' ability to process and understand speech
Two new research papers propose novel frameworks for integrating speech processing with large language models (LLMs). DirectSpeech2LLM aims to mitigate prompt overfitting in Speech-LLMs by using a CTC loss on frozen LLM…
-
Speech LLMs enhanced by translation-based encoder pre-training
A new research paper proposes using speech translation to bridge the gap between speech encoders and large language models (LLMs) in Speech LLMs. The paper argues that current architectures have a structural misalignmen…
-
New framework measures user understanding of speech translation AI
A new research paper introduces a framework for studying users' mental models of speech translation systems. The study uses cross-lingual question answering, where users decide whether to accept machine translation (MT)…
-
New Research Defines Machine Interpreting Design Priorities
A new paper published on arXiv introduces the concept of "machine interpreting" (MI) as a distinct subfield of speech translation, emphasizing the need for evaluation metrics beyond simple textual fidelity. The research…
-
New technique boosts Vietnamese speech translation accuracy
Researchers have developed a new data augmentation technique called Phonetically-Informed Data Augmentation (PiDA) to improve Vietnamese speech translation. The method addresses error propagation in cascaded speech tran…
-
New framework reveals speech translation usability gaps
Researchers have developed Ouvia, a new framework for evaluating speech translation (ST) systems based on user-perceived usability in real-world scenarios. A study involving over 1,750 interactions between English and P…