Search Results for author: Zhihan Li

Found 11 papers, 4 papers with code

Recent Advances in Discrete Speech Tokens: A Review

no code implementations10 Feb 2025 Yiwei Guo, Zhihan Li, Hankun Wang, Bohan Li, Chongtian Shao, Hanglei Zhang, Chenpeng Du, Xie Chen, Shujie Liu, Kai Yu

The rapid advancement of speech generation technologies in the era of large language models (LLMs) has established discrete speech tokens as a foundational paradigm for speech representation.

Language Modeling Language Modelling +1

Why Do Speech Language Models Fail to Generate Semantically Coherent Outputs? A Modality Evolving Perspective

no code implementations22 Dec 2024 Hankun Wang, Haoran Wang, Yiwei Guo, Zhihan Li, Chenpeng Du, Xie Chen, Kai Yu

Although text-based large language models exhibit human-level writing ability and remarkable intelligence, speech language models (SLMs) still struggle to generate semantically coherent outputs.

text-to-speech Text to Speech

LSCodec: Low-Bitrate and Speaker-Decoupled Discrete Speech Codec

no code implementations21 Oct 2024 Yiwei Guo, Zhihan Li, Chenpeng Du, Hankun Wang, Xie Chen, Kai Yu

Voice conversion evaluations prove the satisfactory speaker disentanglement of LSCodec, and ablation study further verifies the effectiveness of the proposed training framework.

Disentanglement Language Modeling +3

vec2wav 2.0: Advancing Voice Conversion via Discrete Token Vocoders

no code implementations3 Sep 2024 Yiwei Guo, Zhihan Li, Junjie Li, Chenpeng Du, Hankun Wang, Shuai Wang, Xie Chen, Kai Yu

To amend the loss of speaker timbre in the content tokens, vec2wav 2. 0 utilizes the WavLM features to provide strong timbre-dependent information.

Speech Synthesis Voice Conversion

Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspective

1 code implementation5 Feb 2024 Zexin Wang, Changhua Pei, Minghua Ma, Xin Wang, Zhihan Li, Dan Pei, Saravan Rajmohan, Dongmei Zhang, QIngwei Lin, Haiming Zhang, Jianhui Li, Gaogang Xie

To ensure an accurate AD, FCVAE exploits an innovative approach to concurrently integrate both the global and local frequency features into the condition of Conditional Variational Autoencoder (CVAE) to significantly increase the accuracy of reconstructing the normal data.

Anomaly Detection Time Series +1

Beyond Sharing: Conflict-Aware Multivariate Time Series Anomaly Detection

1 code implementation17 Aug 2023 Haotian Si, Changhua Pei, Zhihan Li, Yadong Zhao, Jingjing Li, Haiming Zhang, Zulong Diao, Jianhui Li, Gaogang Xie, Dan Pei

Massive key performance indicators (KPIs) are monitored as multivariate time series data (MTS) to ensure the reliability of the software applications and service system.

Anomaly Detection Mixture-of-Experts +4

Model-Agnostic Meta-Learning for Natural Language Understanding Tasks in Finance

no code implementations6 Mar 2023 Bixing Yan, Shaoling Chen, Yuxuan He, Zhihan Li

Our contribution includes: 1. we explore the performance of MAML method with multiple types of tasks: GLUE datasets, SNLI, Sci-Tail and Financial PhraseBank; 2. we study the performance of MAML method with multiple single-type tasks: a real scenario stock price prediction problem with twitter text data.

Language Modeling Language Modelling +4

Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications

10 code implementations12 Feb 2018 Haowen Xu, Wenxiao Chen, Nengwen Zhao, Zeyan Li, Jiahao Bu, Zhihan Li, Ying Liu, Youjian Zhao, Dan Pei, Yang Feng, Jie Chen, Zhaogang Wang, Honglin Qiao

To ensure undisrupted business, large Internet companies need to closely monitor various KPIs (e. g., Page Views, number of online users, and number of orders) of its Web applications, to accurately detect anomalies and trigger timely troubleshooting/mitigation.

Unsupervised Anomaly Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.