94 citations · 196 across the 19 of their papers we have counts for
19 papers
METTS: Multilingual Emotional Text-to-Speech by Cross-speaker and Cross-lingual Emotion Transfer
Xinfa Zhu, Yi Lei, Tao Li +4
Previous multilingual text-to-speech (TTS) approaches have considered leveraging monolingual speaker data to enable cross-lingual speech synthesis. However, such data-efficient app…
HYBRIDFORMER: improving SqueezeFormer with hybrid attention and NSR mechanism
Yuguang Yang, Yu Pan, Jingjing Yin +3
SqueezeFormer has recently shown impressive performance in automatic speech recognition (ASR). However, its inference speed suffers from the quadratic complexity of softmax-attenti…
LMEC: Learnable Multiplicative Absolute Position Embedding Based Conformer for Speech Recognition
Yuguang Yang, Yu Pan, Jingjing Yin +1
This paper proposes a Learnable Multiplicative absolute position Embedding based Conformer (LMEC). It contains a kernelized linear attention (LA) module called LMLA to solve the ti…
DiaCorrect: End-to-end error correction for speaker diarization
Jiangyu Han, Yuhang Cao, Heng Lu +1
In recent years, speaker diarization has attracted widespread attention. To achieve better performance, some studies propose to diarize speech in multiple stages. Although these me…
Improving Cross-lingual Speech Synthesis with Triplet Training Scheme
Jianhao Ye, Hongbin Zhou, Zhiba Su +4
Recent advances in cross-lingual text-to-speech (TTS) made it possible to synthesize speech in a language foreign to a monolingual speaker. However, there is still a large gap betw…
The USTC-Ximalaya system for the ICASSP 2022 multi-channel multi-party meeting transcription (M2MeT) challenge
Maokui He, Xiang Lv, Weilin Zhou +8
We propose two improvements to target-speaker voice activity detection (TS-VAD), the core component in our proposed speaker diarization system that was submitted to the 2022 Multi-…
Phonetic Posteriorgrams based Many-to-Many Singing Voice Conversion via Adversarial Training
Haohan Guo, Heng Lu, Na Hu +5
This paper describes an end-to-end adversarial singing voice conversion (EA-SVC) approach. It can directly generate arbitrary singing waveform by given phonetic posteriorgram (PPG)…
TFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesis
Qiao Tian, Yi Chen, Zewang Zhang +4
Recently, GAN based speech synthesis methods, such as MelGAN, have become very popular. Compared to conventional autoregressive based methods, parallel structures based generators…
FeatherTTS: Robust and Efficient attention based Neural TTS
Qiao Tian, Zewang Zhang, Chao Liu +5
Attention based neural TTS is elegant speech synthesis pipeline and has shown a powerful ability to generate natural speech. However, it is still not robust enough to meet the stab…
Peking Opera Synthesis via Duration Informed Attention Network
Yusong Wu, Shengchen Li, Chengzhu Yu +4
Peking Opera has been the most dominant form of Chinese performing art since around 200 years ago. A Peking Opera singer usually exhibits a very strong personal style via introduci…
DurIAN-SC: Duration Informed Attention Network based Singing Voice Conversion System
Liqiang Zhang, Chengzhu Yu, Heng Lu +6
Singing voice conversion is converting the timbre in the source singing to the target speaker's voice while keeping singing content the same. However, singing data for target speak…
AdaDurIAN: Few-shot Adaptation for Neural Text-to-Speech with DurIAN
Zewang Zhang, Qiao Tian, Heng Lu +2
This paper investigates how to leverage a DurIAN-based average model to enable a new speaker to have both accurate pronunciation and fluent cross-lingual speaking with very limited…
FeatherWave: An efficient high-fidelity neural vocoder with multi-band linear prediction
Qiao Tian, Zewang Zhang, Heng Lu +2
In this paper, we propose the FeatherWave, yet another variant of WaveRNN vocoder combining the multi-band signal processing and the linear predictive coding. The LPCNet, a recentl…
Synthesising Expressiveness in Peking Opera via Duration Informed Attention Network
Yusong Wu, Shengchen Li, Chengzhu Yu +4
This paper presents a method that generates expressive singing voice of Peking opera. The synthesis of expressive opera singing usually requires pitch contours to be extracted as t…
Learning Singing From Speech
Liqiang Zhang, Chengzhu Yu, Heng Lu +5
We propose an algorithm that is capable of synthesizing high quality target speaker's singing voice given only their normal speech samples. The proposed algorithm first integrate s…
PitchNet: Unsupervised Singing Voice Conversion with Pitch Adversarial Network
Chengqi Deng, Chengzhu Yu, Heng Lu +2
Singing voice conversion is to convert a singer's voice to another one's voice without changing singing content. Recent work shows that unsupervised singing voice conversion can be…
DurIAN: Duration Informed Attention Network For Multimodal Synthesis
Chengzhu Yu, Heng Lu, Na Hu +9
In this paper, we present a generic and robust multimodal synthesis system that produces highly natural speech and facial expression simultaneously. The key component of this syste…
Linear networks based speaker adaptation for speech synthesis
Zhiying Huang, Heng Lu, Ming Lei +1
Speaker adaptation methods aim to create fair quality synthesis speech voice font for target speakers while only limited resources available. Recently, as deep neural networks base…
Deep Feed-forward Sequential Memory Networks for Speech Synthesis
Mengxiao Bi, Heng Lu, Shiliang Zhang +2
The Bidirectional LSTM (BLSTM) RNN based speech synthesis system is among the best parametric Text-to-Speech (TTS) systems in terms of the naturalness of generated speech, especial…