1 citations · 2 across the 6 of their papers we have counts for
6 papers
MELD: Mel-Spectrogram-Based Speech Language Modeling with Discrete Latent Variables
Sung-Lin Yeh, Wei Zhou, Gil Keren +6
Recent speech language models rely on encoders that are optimized separately from autoregressive models. Since these encoders are unaware of the downstream objectives, the extracte…
The Llama 4 Herd: Architecture, Training, Evaluation, and Deployment Notes
Redacted by arXiv
This document consolidates publicly reported technical details about Metas Llama 4 model family. It summarizes (i) released variants (Scout and Maverick) and the broader herd conte…
Efficient Streaming LLM for Speech Recognition
Junteng Jia, Gil Keren, Wei Zhou +6
Recent works have shown that prompting large language models with audio encodings can unlock speech recognition capabilities. However, existing techniques do not scale efficiently,…
M-BEST-RQ: A Multi-Channel Speech Foundation Model for Smart Glasses
Yufeng Yang, Desh Raj, Ju Lin +8
The growing popularity of multi-channel wearable devices, such as smart glasses, has led to a surge of applications such as targeted speech recognition and enhanced hearing. Howeve…
Faster Speech-LLaMA Inference with Multi-token Prediction
Desh Raj, Gil Keren, Junteng Jia +2
Large language models (LLMs) have become proficient at solving a wide variety of tasks, including those involving multi-modal inputs. In particular, instantiating an LLM (such as L…
Token-Weighted RNN-T for Learning from Flawed Data
Gil Keren, Wei Zhou, Ozlem Kalinli
ASR models are commonly trained with the cross-entropy criterion to increase the probability of a target token sequence. While optimizing the probability of all tokens in the targe…