English
Related papers

Related papers: Test-Time Training for Speech

200 papers

Acoustic foundation models, fine-tuned for Automatic Speech Recognition (ASR), suffer from performance degradation in wild acoustic test settings when deployed in real-world scenarios. Stabilizing online Test-Time Adaptation (TTA) under…

Sound · Computer Science 2024-10-08 Hongfu Liu , Hengguan Huang , Ye Wang

Machine learning algorithms typically assume that the training and test samples come from the same distributions, i.e., in-distribution. However, in open-world scenarios, streaming big data can be Out-Of-Distribution (OOD), rendering these…

Machine Learning · Computer Science 2022-11-10 Anique Tahir , Lu Cheng , Ruocheng Guo , Huan Liu

Test-time adaptation with pre-trained vision-language models (VLMs) has attracted increasing attention for tackling the issue of distribution shift during the test phase. While prior methods have shown effectiveness in addressing…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Baoshun Tong , Kaiyu Song , Hanjiang Lai

Given the recent success of diffusion in producing natural-sounding synthetic speech, we investigate how diffusion can be used in speaker adaptive TTS. Taking cues from more traditional adaptation approaches, we show that adaptation can be…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-06 Haolin Chen , Philip N. Garner

We propose a method for the task of text-conditioned speech insertion, i.e. inserting a speech sample in an input speech sample, conditioned on the corresponding complete text transcript. An example use case of the task would be to update…

Sound · Computer Science 2025-08-26 Neeraj Matiyali , Siddharth Srivastava , Gaurav Sharma

In recent years, Text-To-Speech (TTS) has been used as a data augmentation technique for speech recognition to help complement inadequacies in the training data. Correspondingly, we investigate the use of a multi-speaker TTS system to…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-25 Yiling Huang , Yutian Chen , Jason Pelecanos , Quan Wang

End-to-end model, especially Recurrent Neural Network Transducer (RNN-T), has achieved great success in speech recognition. However, transducer requires a great memory footprint and computing time when processing a long decoding sequence.…

Sound · Computer Science 2023-07-18 Xiaohui Zhang , Mangui Liang , Zhengkun Tian , Jiangyan Yi , Jianhua Tao

Parallel text-to-speech (TTS) models have recently enabled fast and highly-natural speech synthesis. However, they typically require external alignment models, which are not necessarily optimized for the decoder as they are not jointly…

Sound · Computer Science 2023-03-08 Bac Nguyen , Fabien Cardinaux , Stefan Uhlich

Speaker localization using microphone arrays depends on accurate time delay estimation techniques. For decades, methods based on the generalized cross correlation with phase transform (GCC-PHAT) have been widely adopted for this purpose.…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-22 Axel Berg , Mark O'Connor , Kalle Åström , Magnus Oskarsson

Text mismatch between pre-collected data, either training data or enrollment data, and the actual test data can significantly hurt text-dependent speaker verification (SV) system performance. Although this problem can be solved by carefully…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-07 Yexin Yang , Shuai Wang , Xun Gong , Yanmin Qian , Kai Yu

Despite recent advancements in deep learning, deep neural networks continue to suffer from performance degradation when applied to new data that differs from training data. Test-time adaptation (TTA) aims to address this challenge by…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Sanghun Jung , Jungsoo Lee , Nanhee Kim , Amirreza Shaban , Byron Boots , Jaegul Choo

Deep learning models excel at many tasks but rely on the assumption that training and test data follow the same distribution. This assumption often does not hold in real-world speech systems, where distribution shifts are common due to…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-06 Bronya Roni Chernyak , Yael Segal , Yosi Shrem , Joseph Keshet

Test-Time Training (TTT) models context dependencies by adapting part of the model's weights (referred to as fast weights) during inference. This fast weight, akin to recurrent states in RNNs, stores temporary memories of past tokens in the…

Machine Learning · Computer Science 2025-06-02 Tianyuan Zhang , Sai Bi , Yicong Hong , Kai Zhang , Fujun Luan , Songlin Yang , Kalyan Sunkavalli , William T. Freeman , Hao Tan

Fine-tuning of self-supervised models is a powerful transfer learning method in a variety of fields, including speech processing, since it can utilize generic feature representations obtained from large amounts of unlabeled data.…

Multimedia · Computer Science 2022-12-07 Shinta Otake , Rei Kawakami , Nakamasa Inoue

Test-time augmentation -- the aggregation of predictions across transformed examples of test inputs -- is an established technique to improve the performance of image classification models. Importantly, TTA can be used to improve model…

Machine Learning · Computer Science 2022-06-29 Helen Lu , Divya Shanmugam , Harini Suresh , John Guttag

Best-performing speech models are trained on large amounts of data in the language they are meant to work for. However, most languages have sparse data, making training models challenging. This shortage of data is even more prevalent in…

Computation and Language · Computer Science 2024-10-08 David-Gabriel Ion , Răzvan-Alexandru Smădu , Dumitru-Clementin Cercel , Florin Pop , Mihaela-Claudia Cercel

Handwritten text recognition aims to convert visual input into machine-readable text, and it remains challenging due to the evolving and context-dependent nature of handwriting. Character sets change over time, and character frequency…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Panagiotis Kaliosis , John Pavlopoulos

While Large Language Models (LLMs) have exhibited remarkable emergent capabilities through extensive pre-training, they still face critical limitations in generalizing to specialized domains and handling diverse linguistic variations, known…

Computation and Language · Computer Science 2025-05-28 Jinwu Hu , Zhitian Zhang , Guohao Chen , Xutao Wen , Chao Shuai , Wei Luo , Bin Xiao , Yuanqing Li , Mingkui Tan

To alleviate the data scarcity problem in End-to-end speech translation (ST), pre-training on data for speech recognition and machine translation is considered as an important technique. However, the modality gap between speech and text…

Computation and Language · Computer Science 2022-12-20 Xingshan Zeng , Liangyou Li , Qun Liu

Neural text-to-speech (TTS) models can synthesize natural human speech when trained on large amounts of transcribed speech. However, collecting such large-scale transcribed data is expensive. This paper proposes an unsupervised pre-training…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-29 Seongyeon Park , Myungseo Song , Bohyung Kim , Tae-Hyun Oh