Search Results for author:
Found 13 papers, 1 papers with code
Teacher-Student Training for Debiasing: General Permutation Debiasing for Large Language Models
Large Language Models (LLMs) have demonstrated impressive zero-shot capabilities and versatility in NLP tasks, however they sometimes fail to maintain crucial invariances for specific tasks.
AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs
In this work, we extend the instruction-tuned Llama-2 model with end-to-end general-purpose speech processing and reasoning abilities while maintaining the wide range of original LLM capabilities, without using any carefully curated paired data.
End-to-End Speech Recognition Contextualization with Large Language Models
Overall, we demonstrate that by only adding a handful number of trainable parameters via adapters, we can unlock contextualized speech recognition capability for the pretrained LLM while keeping the same text-only input functionality.
TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models
Results demonstrate that our TODM Supernet either matches or surpasses the performance of manually tuned models by up to a relative of 3% better in word error rate (WER), while efficiently keeping the cost of training many models at a small constant.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Prompting Large Language Models with Speech Recognition Abilities
Furthermore, we perform ablation studies to investigate whether the LLM can be completely frozen during training to maintain its original capabilities, scaling up the audio encoder, and increasing the audio encoder striding to generate fewer embeddings.
Abstractive Text Summarization
Automatic Speech Recognition
+3
CUED at ProbSum 2023: Hierarchical Ensemble of Summarization Models
In this paper, we consider the challenge of summarizing patients' medical progress notes in a limited data setting.
Multi-Head State Space Model for Speech Recognition
State space models (SSMs) have recently shown promising results on small-scale sequence and language modelling tasks, rivalling and outperforming many attention-based approaches.
Ranked #8 on
Speech Recognition
on LibriSpeech test-clean
Logit-Based Ensemble Distribution Distillation for Robust Autoregressive Sequence Uncertainties
Efficiently and reliably estimating uncertainty is an important objective in deep learning.
Who Needs Decoders? Efficient Estimation of Sequence-level Attributes
In these scenarios, where for example knowing the quality of a system's output to predict poor performance prevails over knowing the output itself, is it possible to bypass the autoregressive decoding?
Self-Distribution Distillation: Efficient Uncertainty Estimation
Furthermore it is possible to build ensembles of these models and apply hierarchical ensemble distillation approaches.
Subsequence Based Deep Active Learning for Named Entity Recognition
Active Learning (AL) has been successfully applied to Deep Learning in order to drastically reduce the amount of data required to achieve high performance.
Ensemble Distillation Approaches for Grammatical Error Correction
It is, however, more challenging than the standard tasks investigated for distillation as the prediction of any grammatical correction to a word will be highly dependent on both the input sequence and the generated output history for the word.
Improved Large-margin Softmax Loss for Speaker Diarisation
Speaker diarisation systems nowadays use embeddings generated from speech segments in a bottleneck layer, which are needed to be discriminative for unseen speakers.
