中文
相关论文

相关论文: Synth4Kws: Synthesized Speech for User Defined Key…

200 篇论文

This paper explores the use of TTS synthesized training data for KWS (keyword spotting) task while minimizing development cost and time. Keyword spotting models require a huge amount of training data to be accurate, and obtaining such…

Custom keyword spotting (KWS) allows detecting user-defined spoken keywords from streaming audio. This is achieved by comparing the embeddings from voice enrollments and input audio. State-of-the-art custom KWS models are typically trained…

音频与语音处理 · 电气工程与系统科学 2026-02-06 Pai Zhu , Quan Wang , Dhruuv Agarwal , Kurt Partridge

The development of high-performance, on-device keyword spotting (KWS) systems for ultra-low-power hardware is critically constrained by the scarcity of specialized, multi-command training datasets. Traditional data collection through human…

声音 · 计算机科学 2025-11-25 Lu Gan , Xi Li

The keyword spotting (KWS) problem requires large amounts of real speech training data to achieve high accuracy across diverse populations. Utilizing large amounts of text-to-speech (TTS) synthesized data can reduce the cost and time…

Confusing-words are commonly encountered in real-life keyword spotting applications, which causes severe degradation of performance due to complex spoken terms and various kinds of words that sound similar to the predefined keywords. To…

机器学习 · 计算机科学 2020-11-04 Yan Jia , Zexin Cai , Murong Ma , Zeqing Zhao , Xuyang Wang , Junjie Wang , Ming Li

Spoken keyword spotting (KWS) aims to identify keywords in audio for wide applications, especially on edge devices. Current small-footprint KWS systems focus on efficient model designs. However, their inference performance can decline in…

音频与语音处理 · 电气工程与系统科学 2025-05-21 Yang Xiao , Tianyi Peng , Yanghao Zhou , Rohan Kumar Das

Spoken Keyword Spotting (KWS) is the task of distinguishing between the presence and absence of a keyword in audio. The accuracy of a KWS model hinges on its ability to correctly classify examples close to the keyword and non-keyword…

声音 · 计算机科学 2026-02-06 Harry Zhang , Kurt Partridge , Pai Zhu , Neng Chen , Hyun Jin Park , Dhruuv Agarwal , Quan Wang

Recent advances in text-to-speech (TTS) led to the development of flexible multi-speaker end-to-end TTS systems. We extend state-of-the-art attention-based automatic speech recognition (ASR) systems with synthetic audio generated by a TTS…

计算与语言 · 计算机科学 2020-02-18 Nick Rossenbach , Albert Zeyer , Ralf Schlüter , Hermann Ney

This paper presents a novel data augmentation technique for text-to-speech (TTS), that allows to generate new (text, audio) training examples without requiring any additional data. Our goal is to increase diversity of text conditionings…

Keyword spotting (KWS) enables speech-based user interaction and gradually becomes an indispensable component of smart devices. Recently, end-to-end (E2E) methods have become the most popular approach for on-device KWS tasks. However, there…

音频与语音处理 · 电气工程与系统科学 2022-11-01 Jie Wang , Menglong Xu , Jingyong Hou , Binbin Zhang , Xiao-Lei Zhang , Lei Xie , Fuping Pan

With the rise of low power speech-enabled devices, there is a growing demand to quickly produce models for recognizing arbitrary sets of keywords. As with many machine learning tasks, one of the most challenging parts in the model creation…

音频与语音处理 · 电气工程与系统科学 2020-02-05 James Lin , Kevin Kilgour , Dominik Roblek , Matthew Sharifi

Learning to recognize new keywords with just a few examples is essential for personalizing keyword spotting (KWS) models to a user's choice of keywords. However, modern KWS models are typically trained on large datasets and restricted to a…

音频与语音处理 · 电气工程与系统科学 2021-06-07 Abhijeet Awasthi , Kevin Kilgour , Hassan Rom

End-to-end (E2E) approaches to keyword search (KWS) are considerably simpler in terms of training and indexing complexity when compared to approaches which use the output of automatic speech recognition (ASR) systems. This simplification…

音频与语音处理 · 电气工程与系统科学 2024-07-08 Bolaji Yusuf , Murat Saraçlar

For training a few-shot keyword spotting (FS-KWS) model, a large labeled dataset containing massive target keywords has known to be essential to generalize to arbitrary target keywords with only a few enrollment samples. To alleviate the…

音频与语音处理 · 电气工程与系统科学 2022-10-10 Dongjune Lee , Minchan Kim , Sung Hwan Mun , Min Hyun Han , Nam Soo Kim

User-defined keyword spotting (KWS) is crucial for personalized voice interaction, yet existing methods face several challenges: (1) insufficient discriminability among confusable words, (2) performance inconsistency across speakers with…

音频与语音处理 · 电气工程与系统科学 2026-05-22 Zhiqi Ai , Han Cheng , Shiyi Mu , Xinnuo Li , Yongjin Zhou , Shugong Xu

The potential of synthetic data in text-to-speech (TTS) model training has gained increasing attention, yet its rationality and effectiveness require systematic validation. In this study, we systematically investigate the feasibility of…

声音 · 计算机科学 2025-12-22 Tingxiao Zhou , Leying Zhang , Zhengyang Chen , Yanmin Qian

Few-shot keyword spotting (KWS) aims to detect unknown keywords with limited training samples. A commonly used approach is the pre-training and fine-tuning framework. While effective in clean conditions, this approach struggles with mixed…

声音 · 计算机科学 2024-07-09 Junming Yuan , Ying Shi , LanTian Li , Dong Wang , Askar Hamdulla

While recent neural text-to-speech (TTS) systems perform remarkably well, they typically require a substantial amount of recordings from the target speaker reading in the desired speaking style. In this work, we present a novel 3-step…

音频与语音处理 · 电气工程与系统科学 2021-06-03 Goeric Huybrechts , Thomas Merritt , Giulia Comini , Bartek Perz , Raahil Shah , Jaime Lorenzo-Trueba

Spoken keyword spotting (KWS) deals with the identification of keywords in audio streams and has become a fast-growing technology thanks to the paradigm shift introduced by deep learning a few years ago. This has allowed the rapid embedding…

声音 · 计算机科学 2021-11-23 Iván López-Espejo , Zheng-Hua Tan , John Hansen , Jesper Jensen

Open-vocabulary keyword spotting (KWS), which allows users to customize keywords, has attracted increasingly more interest. However, existing methods based on acoustic models and post-processing train the acoustic model with ASR training…

音频与语音处理 · 电气工程与系统科学 2023-12-18 Ao Zhang , Pan Zhou , Kaixun Huang , Yong Zou , Ming Liu , Lei Xie
‹ 上一页 1 2 3 10 下一页 ›