Related papers: Exploring Efficient-tuning Methods in Self-supervi…

Fine-tuning large pre-trained language models on downstream tasks has become the de-facto learning paradigm in NLP. However, conventional approaches fine-tune all the parameters of the pre-trained model, which becomes prohibitive as the…

Unsupervised cross-lingual speech representation learning (XLSR) has recently shown promising results in speech recognition by leveraging vast amounts of unlabeled data across multiple languages. However, standard XLSR model suffers from…

Singing voice beat tracking is a challenging task, due to the lack of musical accompaniment that often contains robust rhythmic and harmonic patterns, something most existing beat tracking systems utilize and can be essential for estimating…

Self-supervised learning (SSL) models like WavLM can be effectively utilized when building speaker diarization systems but are often large and slow, limiting their use in resource constrained scenarios. Previous studies have explored…

Recent synthetic speech detection models typically adapt a pre-trained SSL model via finetuning, which is computationally demanding. Parameter-Efficient Fine-Tuning (PEFT) offers an alternative. However, existing methods lack the specific…

Different languages have distinct phonetic systems and vary in their prosodic features making it challenging to develop a Text-to-Speech (TTS) model that can effectively synthesise speech in multilingual settings. Furthermore, TTS…

Transformer-based large-scale pre-trained models achieve great success. Fine-tuning is the standard practice for leveraging these models in downstream tasks. Among the fine-tuning methods, adapter-tuning provides a parameter-efficient…

Compressing self-supervised models has become increasingly necessary, as self-supervised models become larger. While previous approaches have primarily focused on compressing the model size, shortening sequences is also effective in…

In the arena of language model fine-tuning, the traditional approaches, such as Domain-Adaptive Pretraining (DAPT) and Task-Adaptive Pretraining (TAPT), although effective, but computational intensive. This research introduces a novel…

Automatic Speech Recognition (ASR) systems have found their use in numerous industrial applications in very diverse domains. Since domain-specific systems perform better than their generic counterparts on in-domain evaluation, the need for…

Self-supervised learned (SSL) speech pre-trained models perform well across various speech processing tasks. Distilled versions of SSL models have been developed to match the needs of on-device speech applications. Though having similar…

Fine-tuning large pre-trained language models for downstream tasks remains a critical challenge in natural language processing. This paper presents an empirical analysis comparing two efficient fine-tuning methods - BitFit and adapter…

We present the SUPERB challenge at SLT 2022, which aims at learning self-supervised speech representation for better performance, generalization, and efficiency. The challenge builds upon the SUPERB benchmark and implements metrics to…

Large pretrained language models (PLMs) are often domain- or task-adapted via fine-tuning or prompting. Finetuning requires modifying all of the parameters and having enough data to avoid overfitting while prompting requires no training and…

The massive amount of trainable parameters in the pre-trained language models (PLMs) makes them hard to be deployed to multiple downstream tasks. To address this issue, parameter-efficient transfer learning methods have been proposed to…

Automatic singing voice understanding tasks, such as singer identification, singing voice transcription, and singing technique classification, benefit from data-driven approaches that utilize deep learning techniques. These approaches work…

Language mismatch is among the most common and challenging domain mismatches in deploying speaker verification (SV) systems. Adversarial reprogramming has shown promising results in cross-language adaptation for SV. The reprogramming is…

Enhancing explainability in speech self-supervised learning (SSL) is important for developing reliable SSL-based speech processing systems. This study probes how speech SSL models encode speaker-specific information via a large-scale…

There are significant challenges for speaker adaptation in text-to-speech for languages that are not widely spoken or for speakers with accents or dialects that are not well-represented in the training data. To address this issue, we…

Audio and speech self-supervised encoder models are now widely used for a lot of different tasks. Many of these models are often trained on clean segmented speech content such as LibriSpeech. In this paper, we look into how the pretraining…