HYPERTTS: Parameter Efficient Adaptation in Text to Speech Using Hypernetworks

Challenge:	Neural text-to-speech (TTS) systems limited to predefined speaker styles or specific sets of speaker IDs.
Approach:	They propose a network that can adapt adapter parameters to new speakers . they compare two domain adaptation settings and find it to be very efficient .
Outcome:	The proposed Adapters improve speech synthesis performance on two domains and compare them with baselines.

Similar Papers

Overview

Challenge

Approach

Outcome

UDAPTER - Efficient Domain Adaptation Using Adapters (2023.eacl-main)

Copied to clipboard

Bhavitvya Malik, Abhinav Ramesh Kashyap, Min-Yen Kan, Soujanya Poria

Responsible & Trustworthy NLP

Challenge:	Using adapters, unsupervised domain adaptation (UDA) is more parameter efficient and requires large-scale data to be effective.
Approach:	They propose to add small bottleneck layers to each layer of a pre-trained language model to make it more parameter efficient by adding adapters.
Outcome:	The proposed methods outperform unsupervised domain adaptation methods such as DANN and DSN in natural language inference and sentiment classification tasks.

Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks (2021.acl-long)

Copied to clipboard

Rabeeh Karimi Mahabadi, Sebastian Ruder, Mostafa Dehghani, James Henderson

Responsible & Trustworthy NLP

Challenge:	State-of-the-art parameter-efficient fine-tuning methods rely on introducing adapter modules between the layers of a pretrained language model.
Approach:	They propose a framework that can learn adapter parameters for all layers and tasks by generating them using shared hypernetworks.
Outcome:	The proposed framework improves performance on the well-known GLUE benchmark while adding only 0.29% parameters per task.

Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning (2023.emnlp-demo)

Copied to clipboard

Clifton Poth, Hannah Sterz, Indraneil Paul, Sukannya Purkayastha, Leon Engländer, Timo Imhof, Ivan Vulić, Sebastian Ruder, Iryna Gurevych, Jonas Pfeiffer

Semantic Text Processing

Challenge:	Adapters is an open-source library that unifies parameter-efficient and modular transfer learning in large language models.
Approach:	They propose to integrate 10 different methods into a unified interface for parameter-efficient and modular transfer learning in large language models.
Outcome:	The proposed library is able to perform on multiple NLP tasks and is open-source.

Multilingual Machine Translation with Hyper-Adapters (2022.emnlp-main)

Copied to clipboard

Christos Baziotis, Mikel Artetxe, James Cross, Shruti Bhosale

Green & Sustainable NLP

Challenge:	Multilingual machine translation suffers from negative interference across languages.
Approach:	They propose a rescaling fix that reduces the number of parameters and enables training larger hyper-networks.
Outcome:	The proposed approach outperforms regular adapters and achieves the same performance with 12 times less parameters.

HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Tasks (2023.findings-acl)

Copied to clipboard

Zhengkun Zhang, Wenya Guo, Xiaojun Meng, Yasheng Wang, Yadao Wang, Xin Jiang, Qun Liu, Zhenglu Yang

Language Models

Challenge:	Pretraining and fine-tuning are the dominant paradigms in natural language processing.
Approach:	They propose a parameter-efficient multitask learning framework that takes trainable hyper-embeddings and visual modality as input and outputs weights for different modules in a pretrained language model.
Outcome:	The proposed framework adds fewer trainable parameters in multi-task learning while achieving superior performances and transfer ability compared to state-of-the-art methods.

Hyperdecoders: Instance-specific decoders for multi-task NLP (2022.findings-emnlp)

Copied to clipboard

Hamish Ivison, Matthew Peters

Responsible & Trustworthy NLP

Challenge:	Recent work in NLP has examined the performance of large pretrained transformer-based models in multi-task settings, where a single model is evaluated on multiple tasks simultaneously.
Approach:	They propose a method for multi-tasking using a hypernetwork conditioned on the output of an encoder to generate a unique decoder adaptation for every input instance.
Outcome:	The proposed method outperforms previous methods for efficient multi-task fine-tuning and maps from encoder representations to output labels.

LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models (2023.emnlp-main)

Copied to clipboard

Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Soujanya Poria, Roy Lee

Language Models

Challenge:	Large language models (LLMs) have shown unprecedented performance across various tasks.
Approach:	They propose an easy-to-use framework that integrates adapters into LLMs . they evaluate adapters on 14 datasets from two different reasoning tasks .
Outcome:	The proposed framework can be used to fine-tune open-access language models with task-specific data and instruction data.

Example-based Hypernetworks for Multi-source Adaptation to Unseen Domains (2023.findings-emnlp)

Copied to clipboard

Tomer Volk, Eyal Ben-David, Ohad Amosy, Gal Chechik, Roi Reichart

Challenge:	In order to achieve unprecedented performance, many out-of-distribution generalization approaches use unlabeled data from the target distribution.
Approach:	They propose a framework that leverages labeled data from multiple source domains to generalize to unknown target domains at training.
Outcome:	The proposed framework outperforms existing models in two tasks, and it is compared to few-shot GPT-3.

Lightweight Adapter Tuning for Multilingual Speech Translation (2021.acl-short)

Copied to clipboard

Hang Le, Juan Pino, Changhan Wang, Jiatao Gu, Didier Schwab, Laurent Besacier

Green & Sustainable NLP

Challenge:	Adapter tuning is an efficient alternative to fine-tuning in NLP . a multilingual model could be outperformed by its bilingual counterparts .
Approach:	They propose to use adapter tuning to optimize for multilingual speech translation . they use pre-trained models to freeze pre-train parameters and inject lightweight modules .
Outcome:	The proposed adapters can specialize to specific language pairs with low extra cost . the proposed models outperform bilingual models on high-resource language pairs .

BnTTS: Few-Shot Speaker Adaptation in Low-Resource Setting (2025.findings-naacl)

Copied to clipboard

Mohammad Jahid Ibna Basher, Md Kowsher, Md Saiful Islam, Rabindra Nath Nandi, Nusrat Jahan Prottasha, Mehadi Hasan Menon, Tareq Al Muntasir, Shammur Absar Chowdhury, Firoj Alam, Niloofar Yousefi, Ozlem Garibay

Low-Resource NLP

Challenge:	Empirical evaluations in few-shot settings show that BnTTS significantly improves the naturalness, intelligibility, and speaker fidelity of synthesized Bangla speech.
Approach:	They propose to integrate Bangla into a multilingual TTS pipeline with modifications to account for the phonetic and linguistic characteristics of the language.
Outcome:	The proposed framework improves the naturalness, intelligibility, and speaker fidelity of synthesized Bangla speech compared to state-of-the-art systems.