1 citations · 1 across the 8 of their papers we have counts for
8 papers
From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization
Chenxi Zhou, Pengfei Cao, Jiang Li +4
Post-Training Quantization (PTQ) is critical for the efficient deployment of Large Language Models (LLMs). While 4-bit quantization is widely regarded as an optimal trade-off, redu…
LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs
Keda Tao, Yuhua Zheng, Jia Xu +13
Recent advancements in omnimodal large language models (OmniLLMs) have significantly improved the comprehension of audio and video inputs. However, current evaluations primarily fo…
Deep Speech Synthesis from Multimodal Articulatory Representations
Peter Wu, Bohan Yu, Kevin Scheck +6
The amount of articulatory data available for training deep learning models is much less compared to acoustic speech data. In order to improve articulatory-to-acoustic synthesis pe…
Fast, High-Quality and Parameter-Efficient Articulatory Synthesis using Differentiable DSP
Yisi Liu, Bohan Yu, Drake Lin +3
Articulatory trajectories like electromagnetic articulography (EMA) provide a low-dimensional representation of the vocal tract filter and have been used as natural, grounded featu…
Towards EMG-to-Speech with a Necklace Form Factor
Peter Wu, Ryan Kaveh, Raghav Nautiyal +8
Electrodes for decoding speech from electromyography (EMG) are typically placed on the face, requiring adhesives that are inconvenient and skin-irritating if used regularly. We exp…
Multimodal Segmentation for Vocal Tract Modeling
Rishi Jain, Bohan Yu, Peter Wu +2
Accurate modeling of the vocal tract is necessary to construct articulatory representations for interpretable speech processing and linguistics. However, vocal tract modeling is ch…
Towards Streaming Speech-to-Avatar Synthesis
Tejas S. Prabhune, Peter Wu, Bohan Yu +1
Streaming speech-to-avatar synthesis creates real-time animations for a virtual character from audio data. Accurate avatar representations of speech are important for the visualiza…
Towards an Interpretable Representation of Speaker Identity via Perceptual Voice Qualities
Robin Netzorg, Bohan Yu, Andrea Guzman +3
Unlike other data modalities such as text and vision, speech does not lend itself to easy interpretation. While lay people can understand how to describe an image or sentence via p…