English
Related papers

Related papers: Mel-spectrogram augmentation for sequence to seque…

200 papers

Previous work on speaker adaptation for end-to-end speech synthesis still falls short in speaker similarity. We investigate an orthogonal approach to the current speaker adaptation paradigms, speaker augmentation, by creating artificial…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-10 Erica Cooper , Cheng-I Lai , Yusuke Yasuda , Junichi Yamagishi

Singing voice separation (SVS) is a task that separates singing voice audio from its mixture with instrumental audio. Previous SVS studies have mainly employed the spectrogram masking method which requires a large dimensionality in…

Sound · Computer Science 2022-11-30 Jaekwon Im , Soonbeom Choi , Sangeon Yong , Juhan Nam

In recent years, deep learning-based approaches have significantly improved the performance of single-channel speech enhancement. However, due to the limitation of training data and computational complexity, real-time enhancement of…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-16 Zehua Zhang , Lu Zhang , Xuyi Zhuang , Yukun Qian , Heng Li , Mingjiang Wang

Capturing high-level structure in audio waveforms is challenging because a single second of audio spans tens of thousands of timesteps. While long-range dependencies are difficult to model directly in the time domain, we show that they can…

Audio and Speech Processing · Electrical Eng. & Systems 2019-06-05 Sean Vasquez , Mike Lewis

Speaker recognition performance has been greatly improved with the emergence of deep learning. Deep neural networks show the capacity to effectively deal with impacts of noise and reverberation, making them attractive to far-field speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-28 Wenda Chen , Jonathan Huang , Tobias Bocklet

Single-channel speech enhancement approaches do not always improve automatic recognition rates in the presence of noise, because they can introduce distortions unhelpful for recognition. Following a trend towards end-to-end training of…

Sound · Computer Science 2021-12-14 Peter Plantinga , Deblin Bagchi , Eric Fosler-Lussier

This work introduces an approach to assessing phrase break in ESL learners' speech with pre-trained language models (PLMs). Different with traditional methods, this proposal converts speech to token sequences, and then leverages the power…

Computation and Language · Computer Science 2022-10-31 Zhiyi Wang , Shaoguang Mao , Wenshan Wu , Yan Xia

The single-speaker singing voice synthesis (SVS) usually underperforms at pitch values that are out of the singer's vocal range or associated with limited training samples. Based on our previous work, this work proposes a…

Sound · Computer Science 2023-09-04 Shaohuan Zhou , Xu Li , Zhiyong Wu , Ying Shan , Helen Meng

Non-autoregressive (non-AR) sequence-to-seqeunce (seq2seq) models for voice conversion (VC) is attractive in its ability to effectively model the temporal structure while enjoying boosted intelligibility and fast inference thanks to non-AR…

Sound · Computer Science 2023-09-18 Wen-Chin Huang , Kazuhiro Kobayashi , Tomoki Toda

Recently, the pre-trained Transformer models have received a rising interest in the field of speech processing thanks to their great success in various downstream tasks. However, most fine-tuning approaches update all the parameters of the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-31 Junyi Peng , Themos Stafylakis , Rongzhi Gu , Oldřich Plchot , Ladislav Mošner , Lukáš Burget , Jan Černocký

We propose a novel explainable machine learning (ML) model that identifies depression from speech, by modeling the temporal dependencies across utterances and utilizing the spectrotemporal information at the vowel level. Our method first…

Sound · Computer Science 2022-10-28 Kexin Feng , Theodora Chaspari

We study a novel neural architecture and its training strategies of speaker encoder for speaker recognition without using any identity labels. The speaker encoder is trained to extract a fixed-size speaker embedding from a spoken utterance…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-28 Ruijie Tao , Kong Aik Lee , Rohan Kumar Das , Ville Hautamäki , Haizhou Li

A sequence-to-sequence model is a neural network module for mapping two sequences of different lengths. The sequence-to-sequence model has three core modules: encoder, decoder, and attention. Attention is the bridge that connects the…

Computation and Language · Computer Science 2018-07-24 Andros Tjandra , Sakriani Sakti , Satoshi Nakamura

In this paper, we focus on improving the performance of the text-dependent speaker verification system in the scenario of limited training data. The speaker verification system deep learning based text-dependent generally needs a large…

Sound · Computer Science 2020-11-24 Xiaoyi Qin , Yaogen Yang , Lin Yang , Xuyang Wang , Junjie Wang , Ming Li

Speaker-dependent modelling can substantially improve performance in speech-based health monitoring applications. While mixed-effect models are commonly used for such speaker adaptation, they require computationally expensive retraining for…

Machine Learning · Computer Science 2025-06-03 Roseline Polle , Agnes Norbury , Alexandra Livia Georgescu , Nicholas Cummins , Stefano Goria

This study discusses the effect of semi-supervised learning in combination with pretrained language models for data-to-text generation. It is not known whether semi-supervised learning is still helpful when a large-scale language model is…

Computation and Language · Computer Science 2022-07-15 Chris van der Lee , Thiago Castro Ferreira , Chris Emmery , Travis Wiltshire , Emiel Krahmer

The vector representations of fixed dimensionality for words (in text) offered by Word2Vec have been shown to be very useful in many application scenarios, in particular due to the semantic information they carry. This paper proposes a…

Sound · Computer Science 2016-06-14 Yu-An Chung , Chao-Chung Wu , Chia-Hao Shen , Hung-Yi Lee , Lin-Shan Lee

Previous research has shown that the principal singular vectors of a pre-trained model's weight matrices capture critical knowledge. In contrast, those associated with small singular values may contain noise or less reliable information. As…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-10 Zhe Li , Man-wai Mak , Mert Pilanci , Hung-yi Lee , Helen Meng

This paper addresses the challenge of enhancing the realism of vocoder-generated singing voice audio by mitigating the distinguishable disparities between synthetic and real-life recordings, particularly in high-frequency spectrogram…

Sound · Computer Science 2025-08-05 Runxuan Yang , Kai Li , Guo Chen , Xiaolin Hu

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. Here speech enhancement methods have traditionally allowed improved…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-28 Yanpei Shi , Qiang Huang , Thomas Hain
‹ Prev 1 8 9 10 Next ›