Related papers: Distilled Non-Semantic Speech Embeddings with Bina…
The training of high-quality, robust machine learning models for speech-driven 3D facial animation requires a large, diverse dataset of high-quality audio-animation pairs. To overcome the lack of such a dataset, recent work has introduced…
Pretrained language models like BERT have achieved good results on NLP tasks, but are impractical on resource-limited devices due to memory footprint. A large fraction of this footprint comes from the input embeddings with large input…
Over the past year, the emergence of transfer learning with large-scale language models (LM) has led to dramatic performance improvements across a broad range of natural language understanding tasks. However, the size and memory footprint…
Large language models (LLMs) provide robots with powerful contextual reasoning abilities and a natural human interface. Yet, current LLM-enabled robots typically depend on cloud-hosted models, limiting their usability in environments with…
The performance of speaker diarization is strongly affected by its clustering algorithm at the test stage. However, it is known that clustering algorithms are sensitive to random noises and small variations, particularly when the clustering…
Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with…
Large pre-trained multilingual models like mBERT, XLM-R achieve state of the art results on language understanding tasks. However, they are not well suited for latency critical applications on both servers and edge devices. It's important…
Ensuring that Large Language Models (LLMs) generate text representative of diverse sub-populations is essential, particularly when key concepts related to under-represented groups are scarce in the training data. We address this challenge…
The current era of Natural Language Processing (NLP) is dominated by Transformer models. However, novel architectures relying on recurrent mechanisms, such as xLSTM and Mamba, have been proposed as alternatives to attention-based models.…
Large self-supervised models are effective feature extractors, but their application is challenging under on-device budget constraints and biased dataset collection, especially in keyword spotting. To address this, we proposed a knowledge…
Byte Language Models (BLMs) have emerged as a promising direction for scaling language models beyond tokenization. However, existing BLMs typically require training from scratch on trillions of bytes, making them prohibitively expensive. In…
Knowledge distillation from large language models (LLMs) assumes that the teacher's output distribution is a high-quality training signal. On reasoning tasks, this assumption is frequently violated. A model's intermediate representations…
We perform knowledge distillation (KD) benchmark from task-specific BERT-base teacher models to various student models: BiLSTM, CNN, BERT-Tiny, BERT-Mini, and BERT-Small. Our experiment involves 12 datasets grouped in two tasks: text…
The upscaling of Large Language Models (LLMs) has yielded impressive advances in natural language processing, yet it also poses significant deployment challenges. Weight quantization has emerged as a widely embraced solution to reduce…
Deploying large language models (LLMs) in resource-constrained environments is hindered by heavy computational and memory requirements. We present LBLLM, a lightweight binarization framework that achieves effective W(1+1)A4 quantization…
Dataset distillation, a training-aware data compression technique, has recently attracted increasing attention as an effective tool for mitigating costs of optimization and data storage. However, progress remains largely empirical.…
The remarkable performance of the pre-trained language model (LM) using self-supervised learning has led to a major paradigm shift in the study of natural language processing. In line with these changes, leveraging the performance of speech…
The deep neural networks, such as the Deep-FSMN, have been widely studied for keyword spotting (KWS) applications. However, computational resources for these networks are significantly constrained since they usually run on-call on edge…
Language models pre-trained on biomedical corpora, such as BioBERT, have recently shown promising results on downstream biomedical tasks. Many existing pre-trained models, on the other hand, are resource-intensive and computationally heavy…
Knowledge Distillation is an effective method of transferring knowledge from a large model to a smaller model. Distillation can be viewed as a type of model compression, and has played an important role for on-device ASR applications. In…