English
Related papers

Related papers: Augmenting Transformer-Transducer Based Speaker Ch…

200 papers

Building multispeaker neural network-based text-to-speech synthesis systems commonly relies on the availability of large amounts of high quality recordings from each speaker and conditioning the training process on the speaker's identity or…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-04 Beata Lorincz , Adriana Stan , Mircea Giurgiu

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

Mispronunciation detection and diagnosis (MDD) technology is a key component of computer-assisted pronunciation training system (CAPT). In the field of assessing the pronunciation quality of constrained speech, the given transcriptions can…

Sound · Computer Science 2022-06-16 Linkai Peng , Yingming Gao , Binghuai Lin , Dengfeng Ke , Yanlu Xie , Jinsong Zhang

Recent synthetic speech detectors leveraging the Transformer model have superior performance compared to the convolutional neural network counterparts. This improvement could be due to the powerful modeling ability of the multi-head…

Sound · Computer Science 2024-09-10 Duc-Tuan Truong , Ruijie Tao , Tuan Nguyen , Hieu-Thi Luong , Kong Aik Lee , Eng Siong Chng

Recently, Transformers have gained significant popularity in image restoration tasks such as image super-resolution and denoising, owing to their superior performance. However, balancing performance and computational burden remains a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Leheng Zhang , Wei Long , Yawei Li , Xingyu Zhou , Xiaorui Zhao , Shuhang Gu

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

Adversarial attack approaches to speaker identification either need high computational cost or are not very effective, to our knowledge. To address this issue, in this paper, we propose a novel generation-network-based approach, called…

Sound · Computer Science 2023-02-28 Jiadi Yao , Xing Chen , Xiao-Lei Zhang , Wei-Qiang Zhang , Kunde Yang

Zero-shot multi-speaker TTS aims to synthesize speech with the voice of a chosen target speaker without any fine-tuning. Prevailing methods, however, encounter limitations at adapting to new speakers of out-of-domain settings, primarily due…

Sound · Computer Science 2024-03-06 Yejin Jeon , Yunsu Kim , Gary Geunbae Lee

The recent emergence of joint CTC-Attention model shows significant improvement in automatic speech recognition (ASR). The improvement largely lies in the modeling of linguistic information by decoder. The decoder joint-optimized with an…

Computation and Language · Computer Science 2022-10-27 Xulong Zhang , Jianzong Wang , Ning Cheng , Mengyuan Zhao , Zhiyong Zhang , Jing Xiao

We propose a novel two-stage text-to-speech (TTS) framework with two types of discrete tokens, i.e., semantic and acoustic tokens, for high-fidelity speech synthesis. It features two core components: the Interpreting module, which processes…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-26 Joun Yeop Lee , Myeonghun Jeong , Minchan Kim , Ji-Hyun Lee , Hoon-Young Cho , Nam Soo Kim

We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages,…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-28 Minchan Kim , Myeonghun Jeong , Byoung Jin Choi , Semin Kim , Joun Yeop Lee , Nam Soo Kim

RNN-Transducer (RNN-T) is a widely adopted architecture in speech recognition, integrating acoustic and language modeling in an end-to-end framework. However, the RNN-T predictor tends to over-rely on consecutive word dependencies in…

Sound · Computer Science 2025-02-21 Khanh Le , Tuan Vu Ho , Dung Tran , Duc Thanh Chau

Fine-tuning is a popular method for adapting text-to-speech (TTS) models to new speakers. However this approach has some challenges. Usually fine-tuning requires several hours of high quality speech per speaker. There is also that…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-02 Cheng-Ping Hsieh , Subhankar Ghosh , Boris Ginsburg

The SpeakerBeam-FE (SBF) method is proposed for speaker extraction. It attempts to overcome the problem of unknown number of speakers in an audio recording during source separation. The mask approximation loss of SBF is sub-optimal, which…

Audio and Speech Processing · Electrical Eng. & Systems 2019-03-26 Chenglin Xu , Wei Rao , Eng Siong Chng , Haizhou Li

We introduce a text-to-speech(TTS) framework based on a neural transducer. We use discretized semantic tokens acquired from wav2vec2.0 embeddings, which makes it easy to adopt a neural transducer for the TTS framework enjoying its monotonic…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-09 Minchan Kim , Myeonghun Jeong , Byoung Jin Choi , Dongjune Lee , Nam Soo Kim

Target sound detection (TSD) aims to detect the target sound from mixture audio given the reference information. Previous works have shown that TSD models can be trained on fully-annotated (frame-level label) or weakly-annotated (clip-level…

Sound · Computer Science 2022-07-20 Dongchao Yang , Helin Wang , Yuexian Zou , Wenwu Wang

Modern speaker recognition system relies on abundant and balanced datasets for classification training. However, diverse defective datasets, such as partially-labelled, small-scale, and imbalanced datasets, are common in real-world…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-03 Ruijie Tao , Zhan Shi , Yidi Jiang , Tianchi Liu , Haizhou Li

Recently, language identity information has been utilized to improve the performance of end-to-end code-switching (CS) speech recognition. However, previous works use an additional language identification (LID) model as an auxiliary module,…

Computation and Language · Computer Science 2020-02-20 Shuai Zhang , Jiangyan Yi , Zhengkun Tian , Jianhua Tao , Ye Bai

End-to-end models are fast replacing the conventional hybrid models in automatic speech recognition. Transformer, a sequence-to-sequence model, based on self-attention popularly used in machine translation tasks, has given promising results…

Audio and Speech Processing · Electrical Eng. & Systems 2021-11-19 Vishwas M. Shetty , Metilda Sagaya Mary N J , S. Umesh

Current direct speech-to-speech translation methods predominantly employ speech tokens as intermediate representations. However, a single speech token is not dense in semantics, so we generally need multiple tokens to express a complete…

Computation and Language · Computer Science 2025-10-14 Jianjin Wang , Runsong Zhao , Xiaoqian Liu , Yuan Ge , Ziqiang Xu , Tong Xiao , Shengxiang Gao , Zhengtao Yu , Jingbo Zhu