Kai Liu

21 papers A 4Misc 4Journal 9Unranked 4
YearRankTypeTitle / Venue / Authors
2025 Misc conf
CAMEL: Cross-Attention Enhanced Mixture-of-Experts and Language Bias for Code-Switching Speech Recognition.
ICASSP
He Wang, Xucheng Wan, Naijun Zheng, Kai Liu, Huan Zhou, Guojian Li, Lei Xie
2025 Misc conf
SCDiar: a streaming diarization system based on speaker change detection and speech recognition.
ICASSP
Naijun Zheng, Xucheng Wan, Kai Liu, Huan Zhou
2025 J jnl
SCDiar: a streaming diarization system based on speaker change detection and speech recognition.
CoRR
Naijun Zheng, Xucheng Wan, Kai Liu, Huan Zhou
2024 A conf
An efficient text augmentation approach for contextualized Mandarin speech recognition.
INTERSPEECH
Naijun Zheng, Xucheng Wan, Kai Liu, Ziqing Du, Huan Zhou
2024 J jnl
An efficient text augmentation approach for contextualized Mandarin speech recognition.
CoRR
Naijun Zheng, Xucheng Wan, Kai Liu, Ziqing Du, Huan Zhou
2024 J jnl
CAMEL: Cross-Attention Enhanced Mixture-of-Experts and Language Bias for Code-Switching Speech Recognition.
CoRR
He Wang, Xucheng Wan, Naijun Zheng, Kai Liu, Huan Zhou, Guojian Li, Lei Xie
2024 A conf
Real-time scheme for rapid extraction of speaker embeddings in challenging recording conditions.
INTERSPEECH
Kai Liu, Ziqing Du, Huan Zhou, Xucheng Wan, Naijun Zheng
2024 J jnl
XCB: an effective contextual biasing approach to bias cross-lingual phrases in speech recognition.
CoRR
Xucheng Wan, Naijun Zheng, Kai Liu, Huan Zhou
2023 J jnl
Improving Target Speaker Extraction with Sparse LDA-transformed Speaker Embeddings.
CoRR
Kai Liu, Xucheng Wan, Ziqing Du, Huan Zhou
2023 Misc conf
X-SEPFORMER: End-To-End Speaker Extraction Network with Explicit Optimization on Speaker Confusion.
ICASSP
Kai Liu, Ziqing Du, Xucheng Wan, Huan Zhou
2023 J jnl
X-SepFormer: End-to-end Speaker Extraction Network with Explicit Optimization on Speaker Confusion.
CoRR
Kai Liu, Ziqing Du, Xucheng Wan, Huan Zhou
2022 J jnl
Joint Speech Activity and Overlap Detection with Multi-Exit Architecture.
CoRR
Ziqing Du, Kai Liu, Xucheng Wan, Huan Zhou
2022 J jnl
Speech Enhancement with Perceptually-motivated Optimization and Dual Transformations.
CoRR
Xucheng Wan, Kai Liu, Ziqing Du, Huan Zhou
2021 — conf
Multi-Band Melgan: Faster Waveform Generation For High-Quality Text-To-Speech.
SLT
Geng Yang, Shan Yang, Kai Liu, Peng Fang, Wei Chen, Lei Xie
2021 A conf
Online Speaker Diarization Equipped with Discriminative Modeling and Guided Inference.
Interspeech
Xucheng Wan, Kai Liu, Huan Zhou
2020 J jnl
Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speech.
CoRR
Geng Yang, Shan Yang, Kai Liu, Peng Fang, Wei Chen, Lei Xie
2020 A conf
Speech Emotion Recognition with Discriminative Feature Learning.
INTERSPEECH
Huan Zhou, Kai Liu
2020 Misc conf
Text-Independent Speaker Verification with Adversarial Learning on Short Utterances.
ICASSP
Kai Liu, Huan Zhou
2020 — conf
The Sogou System for Blizzard Challenge 2020.
Blizzard Challenge / Voice Conversion Challenge
Fanbo Meng, Ruimin Wang, Peng Fang, Shuangyuan Zou, Wenjun Duan, Ming Zhou, Kai Liu, Wei Chen
2019 — conf
SZ-NPU Team's Entry to Blizzard Challenge 2019.
Blizzard Challenge
Shan Yang, Wenshuo Ge, Fengyu Yang, Xinyong Zhou, Fanbo Meng, Kai Liu, Lei Xie
2018 — conf
The Sogou speech synthesis system for Blizzard Challenge 2018.
Blizzard Challenge
Kai Liu, Fanbo Meng, Yang Song, Bo Fan, Wenjun Duan, Wei Chen