Papers by Tom Ko

8 papers
MOSPC: MOS Prediction Based on Pairwise Comparison (2023.acl-short)

Copied to clipboard

Challenge: et al., 2016a) show that MOS prediction model can improve ranking accuracy of speech quality.
Approach: They propose a general framework for MOS prediction based on pair comparison . they use C-Mixup algorithm to enhance generalization performance of MOSPC .
Outcome: The proposed model outperforms baselines on most correlation coefficient metrics . it also surpasses the strong baseline in ranking accuracy on each fine-grained segment.
RepCodec: A Speech Representation Codec for Speech Tokenization (2024.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models have led to discrete speech tokenization, but this discretization can be costly and impedes performance.
Approach: They propose a new speech representation codec for semantic speech tokenization that reconstructs speech representations from speech encoders like HuBERT or data2vec.
Outcome: The proposed method outperforms the widely used k-means clustering approach in speech understanding and generation.
Parameter-Efficient Transfer Learning for End-to-end Speech Translation (2024.lrec-main)

Copied to clipboard

Challenge: Existing approaches to improve end-to-end speech translation are limited by the availability of labeled data.
Approach: They propose a method which utilizes two lightweight adaptation techniques to modulate Attention and the Feed-Forward Network while preserving the capabilities of pre-trained models.
Outcome: The proposed method outperforms baseline models and significantly improves performance in low-resource settings.
CTC-based Non-autoregressive Speech Translation (2023.acl-long)

Copied to clipboard

Challenge: End-to-end speech translation (E2E ST) and non-autoregressive (NAR) generation are promising in language and speech processing for their advantages of less error propagation and low latency.
Approach: They develop a model that uses connectionist temporal classification to predict the source and target texts.
Outcome: The proposed model achieves an average BLEU score of 29.5 with a speed-up of 5.67.
Selective Prompting Tuning for Personalized Conversations with LLMs (2024.findings-acl)

Copied to clipboard

Challenge: Personalization in conversational AI requires persona profiles and contextual understanding to create meaningful conversations.
Approach: They propose a method that softly prompts LLMs for personalized conversations in a selective way.
Outcome: The proposed approach improves response diversity by up to 90% on the CONVAI2 dataset.
Learning Retrieval Augmentation for Personalized Dialogue Generation (2023.emnlp-main)

Copied to clipboard

Challenge: Personalized dialogue generation is a popular approach for conversational AI applications . however, persona profiles may not provide comprehensive descriptions of the persona .
Approach: They propose a method that leverages persona profiles and dialogue context to generate personalized dialogues by leveraging personas and persona profile.
Outcome: The proposed method outperforms baselines on the CONVAI2 dataset . it is expected to generate personalized dialogues based on persona profiles and dialogue context .
DUB: Discrete Unit Back-translation for Speech Translation (2023.findings-acl)

Copied to clipboard

Challenge: Discrete unit back-translation (DUB) is a back-translated speech-to-text translation (ST) technique that can be applied to ST . a modality gap between speech and text makes it difficult to transfer these techniques to ST due to the modality of the speech-text model.
Approach: They propose a method to represent speech with discrete units instead of continuous features in direct ST.
Outcome: The proposed method achieves comparable performance to existing methods that rely on large-scale external data.
SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing (2022.acl-long)

Copied to clipboard

Challenge: Existing work shows that pre-trained models can improve in various natural language processing tasks.
Approach: They propose a unified-modal encoder-decoder framework that pre-trains speech-text representations using large-scale unlabeled speech and text data.
Outcome: The proposed framework is superior to existing models on speech-to-text processing tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations