Related papers: Test-Time Training for Speech
Data samples generated by several real world processes are dynamic in nature \textit{i.e.}, their characteristics vary with time. Thus it is not possible to train and tackle all possible distributional shifts between training and inference,…
Test-time domain adaptation aims to adapt a source pre-trained model to a target domain without using any source data. Existing works mainly consider the case where the target domain is static. However, real-world machine perception systems…
Pre-trained vision-language models (e.g., CLIP) have shown promising zero-shot generalization in many downstream tasks with properly designed text prompts. Instead of relying on hand-engineered prompts, recent works learn prompts using the…
Few-shot learning-the ability to train models with access to limited data-has become increasingly popular in the natural language processing (NLP) domain, as large language models such as GPT and T0 have been empirically shown to achieve…
The GPT (Generative Pre-trained Transformer) language models are an artificial intelligence and natural language processing technology that enables automatic text generation. There is a growing interest in applying GPT language models to…
Phrase break prediction is a crucial task for improving the prosody naturalness of a text-to-speech (TTS) system. However, most proposed phrase break prediction models are monolingual, trained exclusively on a large amount of labeled data.…
Discourse analysis allows us to attain inferences of a text document that extend beyond the sentence-level. The current performance of discourse models is very low on texts outside of the training distribution's coverage, diminishing the…
The conventional modus operandi for adapting pre-trained vision-language models (VLMs) during test-time involves tuning learnable prompts, ie, test-time prompt tuning. This paper introduces Test-Time Low-rank adaptation (TTL) as an…
Adapting a neural text-to-speech (TTS) model to a target speaker typically involves fine-tuning most if not all of the parameters of a pretrained multi-speaker backbone model. However, serving hundreds of fine-tuned neural TTS models is…
The mechanism proposed here is for real-time speaker change detection in conversations, which firstly trains a neural network text-independent speaker classifier using in-domain speaker data. Through the network, features of conversational…
This paper aims to build a multi-speaker expressive TTS system, synthesizing a target speaker's speech with multiple styles and emotions. To this end, we propose a novel contrastive learning-based TTS approach to transfer style and emotion…
Recently, neural networks based purely on self-attention, such as the Vision Transformer (ViT), have been shown to outperform deep learning models constructed with convolutional neural networks (CNNs) on various vision tasks, thus extending…
Time-series forecasting has seen significant advancements with the introduction of token prediction mechanisms such as multi-head attention. However, these methods often struggle to achieve the same performance as in language modeling,…
Training machine learning algorithms for speech applications requires large, labeled training data sets. This is problematic for clinical applications where obtaining such data is prohibitively expensive because of privacy concerns or lack…
Automatic speech recognition is a difficult problem in pattern recognition because several sources of variability exist in the speech input like the channel variations, the input might be clean or noisy, the speakers may have different…
Speech emotion recognition (SER) has garnered increasing attention due to its wide range of applications in various fields, including human-machine interaction, virtual assistants, and mental health assistance. However, existing SER methods…
This paper investigates test-time adaptation (TTA) for regression, where a regression model pre-trained in a source domain is adapted to an unknown target distribution with unlabeled target data. Although regression is one of the…
This study addresses the issue of speaker gender bias in Speech Translation (ST) systems, which can lead to offensive and inaccurate translations. The masculine bias often found in large-scale ST systems is typically perpetuated through…
Modern text-to-speech (TTS) systems are able to generate audio that sounds almost as natural as human speech. However, the bar of developing high-quality TTS systems remains high since a sizable set of studio-quality <text, audio> pairs is…
This paper proposes a novel test-time adaptation strategy that adjusts the model pre-trained on the source domain using only unlabeled online data from the target domain to alleviate the performance degradation due to the distribution shift…