565 citations · 632 across the 20 of their papers we have counts for
7 papers · 1 filter
FoleyGen: Visually-Guided Audio Generation
Xinhao Mei, Varun Nagaraja, Gael Le Lan +4
Recent advancements in audio generation have been spurred by the evolution of large-scale deep learning models and expansive datasets. However, the task of video-to-audio (V2A) gen…
Stack-and-Delay: a new codebook pattern for music generation
Gael Le Lan, Varun Nagaraja, Ernie Chang +5
In language modeling based music generation, a generated waveform is represented by a sequence of hierarchical token stacks that can be decoded either in an auto-regressive manner…
Enhance audio generation controllability through representation similarity regularization
Yangyang Shi, Gael Le Lan, Varun Nagaraja +6
This paper presents an innovative approach to enhance control over audio generation by emphasizing the alignment between audio and text representations during model training. In th…
Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognition
Yang Li, Liangzhen Lai, Yuan Shangguan +5
Transformer-based models excel in speech recognition. Existing efforts to optimize Transformer inference, typically for long-context applications, center on simplifying attention s…
Low-Resource Cross-Lingual Adaptive Training for Nigerian Pidgin
Pin-Jie Lin, Muhammed Saeed, Ernie Chang +1
Developing effective spoken language processing systems for low-resource languages poses several challenges due to the lack of parallel data and limited resources for fine-tuning m…
Revisiting Sample Size Determination in Natural Language Understanding
Ernie Chang, Muhammad Hassan Rashid, Pin-Jie Lin +4
Knowing exactly how many data points need to be labeled to achieve a certain model performance is a hugely beneficial step towards reducing the overall budgets for annotation. It p…
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
Zechun Liu, Barlas Oguz, Changsheng Zhao +6
Several post-training quantization methods have been applied to large language models (LLMs), and have been shown to perform well down to 8-bits. We find that these methods break d…