paper-with-me

Papers

Assem-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniques

2021-04-02 · Kang-wook Kim, Seung-won Park, Junhyeok Lee, Myun-chul Joe

Recent works on voice conversion (VC) focus on preserving the rhythm and the intonation as well as the linguistic content. To preserve these features from the source, we decompose current non-parallel VC systems into two encoders and one decoder. We analyze each module with several experiments and reassemble the best components to propose Assem-VC, a new state-of-the-art any-to-many non-parallel VC system. We also examine that PPG and Cotatron features are speaker-dependent, and attempt to remove speaker identity with adversarial training. Code and audio samples are available at https://github.com/mindslab-ai/assem-vc.

📄 PDF Abstract BibTeX arXiv:2104.00931

Code (1)

mindslab-ai/assem-vc 공식 구현 pytorch

Tasks

DecoderRhythmSpeech SynthesisVoice Conversion

Similar Papers 제목 키워드 기반

Voice Conversion for Stuttered Speech, Instruments, Unseen Languages and Textually Described Voices

2023-10-12 · Matthew Baas, Herman Kamper

Voice conversion aims to convert source speech into a target voice using recordings of the target speaker as a reference. Newer models are producing increasingly realistic output. But what happens when models are fed wit…

Voice Conversion

HiFi-VC: High Quality ASR-Based Voice Conversion

2022-03-31 · A. Kashkin, I. Karpukhin, S. Shishkin

The goal of voice conversion (VC) is to convert input voice to match the target speaker's voice while keeping text and prosody intact. VC is usually used in entertainment and speaking-aid systems, as well as applied for …

speech-recognitionSpeech RecognitionVocal Bursts Intensity PredictionVoice Conversion

Defense Against Synthetic Speech: Real-Time Detection of RVC Voice Conversion Attacks

2025-12-31 · Prajwal Chinchmalatpure, Suyash Chinchmalatpure, Siddharth Chavan arxiv

Generative audio technologies now enable highly realistic voice cloning and real-time voice conversion, increasing the risk of impersonation, fraud, and misinformation in communication channels such as phone and video ca…

Voice Conversion

ArraMon: A Joint Navigation-Assembly Instruction Interpretation Task in Dynamic Environments

2020-11-15 · Findings of the Association for Computational Linguistics 2020 · Hyounghun Kim, Abhay Zala, Graham Burri, Hao Tan 외

For embodied agents, navigation is an important ability but not an isolated goal. Agents are also expected to perform specific tasks after reaching the target location, such as picking up objects and assembling them into…

Referring ExpressionReferring Expression ComprehensionVision and Language Navigation

Disassembling Object Representations without Labels

2020-04-03 · Zunlei Feng, Xinchao Wang, Yongming He, Yike Yuan 외

In this paper, we study a new representation-learning task, which we termed as disassembling object representations. Given an image featuring multiple objects, the goal of disassembling is to acquire a latent representat…

General ClassificationGenerative Adversarial NetworkObjectRepresentation Learning+1