English
Related papers

Related papers: Augmenting Transformer-Transducer Based Speaker Ch…

200 papers

Remote Sensing Change Detection (RSCD) typically identifies changes in land cover or surface conditions by analyzing multi-temporal images. Currently, most deep learning-based methods primarily focus on learning unimodal visual information,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Yixiao Liu , Yizhou Yang , Jinwen Li , Jun Tao , Ruoyu Li , Xiangkun Wang , Min Zhu , Junlong Cheng

Recent speech synthesis systems based on sampling from autoregressive neural networks models can generate speech almost undistinguishable from human recordings. However, these models require large amounts of data. This paper shows that the…

Computation and Language · Computer Science 2018-11-26 Javier Latorre , Jakub Lachowicz , Jaime Lorenzo-Trueba , Thomas Merritt , Thomas Drugman , Srikanth Ronanki , Klimkov Viacheslav

We introduce a self-supervised speech pre-training method called TERA, which stands for Transformer Encoder Representations from Alteration. Recent approaches often learn by using a single auxiliary task like contrastive prediction,…

Audio and Speech Processing · Electrical Eng. & Systems 2021-08-05 Andy T. Liu , Shang-Wen Li , Hung-yi Lee

Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute --…

Computation and Language · Computer Science 2022-02-14 Chak-Fai Li , Francis Keith , William Hartmann , Matthew Snover

An increasing number of people in the world today speak a mixed-language as a result of being multilingual. However, building a speech recognition system for code-switching remains difficult due to the availability of limited resources and…

Computation and Language · Computer Science 2020-04-30 Genta Indra Winata , Samuel Cahyawijaya , Zhaojiang Lin , Zihan Liu , Peng Xu , Pascale Fung

Learning an effective speaker representation is crucial for achieving reliable performance in speaker verification tasks. Speech signals are high-dimensional, long, and variable-length sequences containing diverse information at each…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-25 Wei Xia , John H. L. Hansen

Target-speaker voice activity detection (TS-VAD) has recently shown promising results for speaker diarization on highly overlapped speech. However, the original model requires a fixed (and known) number of speakers, which limits its…

Audio and Speech Processing · Electrical Eng. & Systems 2021-08-10 Maokui He , Desh Raj , Zili Huang , Jun Du , Zhuo Chen , Shinji Watanabe

Modern large language models use a fixed tokenizer to effectively compress text drawn from a source domain. However, applying the same tokenizer to a new target domain often leads to inferior compression, more costly inference, and reduced…

Computation and Language · Computer Science 2024-11-07 Zhili Feng , Tanya Marwah , Nicolo Fusi , David Alvarez-Melis , Lester Mackey

The recurrent neural network transducer (RNN-T) objective plays a major role in building today's best automatic speech recognition (ASR) systems for production. Similarly to the connectionist temporal classification (CTC) objective, the…

Computation and Language · Computer Science 2022-04-01 Niko Moritz , Takaaki Hori , Shinji Watanabe , Jonathan Le Roux

In this paper, we propose an effective sound event detection (SED) method based on the audio spectrogram transformer (AST) model, pretrained on the large-scale AudioSet for audio tagging (AT) task, termed AST-SED. Pretrained AST models have…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-08 Kang Li , Yan Song , Li-Rong Dai , Ian McLoughlin , Xin Fang , Lin Liu

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…

This paper proposes speaker-adaptive neural vocoders for parametric text-to-speech (TTS) systems. Recently proposed WaveNet-based neural vocoding systems successfully generate a time sequence of speech signal with an autoregressive…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-04 Eunwoo Song , Jin-Seob Kim , Kyungguen Byun , Hong-Goo Kang

Transformer encoder with connectionist temporal classification (CTC) framework is widely used for automatic speech recognition (ASR). However, knowledge distillation (KD) for ASR displays a problem of disagreement between teacher-student…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-13 Eungbeom Kim , Hantae Kim , Kyogu Lee

This paper proposes Transducers with Pronunciation-aware Embeddings (PET). Unlike conventional Transducers where the decoder embeddings for different tokens are trained independently, the PET model's decoder embedding incorporates shared…

Computation and Language · Computer Science 2024-04-09 Hainan Xu , Zhehuai Chen , Fei Jia , Boris Ginsburg

The teacher-student (T/S) learning has been shown effective in unsupervised domain adaptation [1]. It is a form of transfer learning, not in terms of the transfer of recognition decisions, but the knowledge of posteriori probabilities in…

Audio and Speech Processing · Electrical Eng. & Systems 2019-05-01 Zhong Meng , Jinyu Li , Yifan Gong , Biing-Hwang , Juang

Current speech enhancement (SE) research has largely neglected channel attention and spatial attention, and encoder-decoder architecture-based networks have not adequately considered how to provide efficient inputs to the intermediate…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-12 Junyu Wang

Target speech extraction (TSE) systems are designed to extract target speech from a multi-talker mixture. The popular training objective for most prior TSE networks is to enhance reconstruction performance of extracted speech waveform.…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-10 Kai Liu , Ziqing Du , Xucheng Wan , Huan Zhou

Discrete audio tokens have recently gained attention for their potential to bridge the gap between audio and language processing. Ideal audio tokens must preserve content, paralinguistic elements, speaker identity, and many other audio…

Recently, end-to-end speaker extraction has attracted increasing attention and shown promising results. However, its performance is often inferior to that of a blind source separation (BSS) counterpart with a similar network architecture,…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-05 Zifeng Zhao , Dongchao Yang , Rongzhi Gu , Haoran Zhang , Yuexian Zou

Surface defect detection plays an increasingly important role in manufacturing industry to guarantee the product quality. Many deep learning methods have been widely used in surface defect detection tasks, and have been proven to perform…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Jiahui Cheng , Bin Guo , Jiaqi Liu , Sicong Liu , Guangzhi Wu , Yueqi Sun , Zhiwen Yu