paper-with-me

Papers

Scaling NVIDIA's Multi-speaker Multi-lingual TTS Systems with Zero-Shot TTS to Indic Languages

2024-01-24 · Akshit Arora, Rohan Badlani, Sungwon Kim, Rafael Valle, Bryan Catanzaro

In this paper, we describe the TTS models developed by NVIDIA for the MMITS-VC (Multi-speaker, Multi-lingual Indic TTS with Voice Cloning) 2024 Challenge. In Tracks 1 and 2, we utilize RAD-MMM to perform few-shot TTS by training additionally on 5 minutes of target speaker data. In Track 3, we utilize P-Flow to perform zero-shot TTS by training on the challenge dataset as well as external datasets. We use HiFi-GAN vocoders for all submissions. RAD-MMM performs competitively on Tracks 1 and 2, while P-Flow ranks first on Track 3, with mean opinion score (MOS) 4.4 and speaker similarity score (SMOS) of 3.62.

📄 PDF Abstract BibTeX arXiv:2401.13851

Code (0)

등록된 구현이 없습니다.

Tasks

Voice Cloning

Methods 이 논문이 사용한 방법론

HiFi-GAN HiFi-GAN is a generative adversarial network for speech synthesis. HiFi-GAN consists of one generator and two discriminators: multi-scale and multi-period discriminators. The…

Similar Papers 제목 키워드 기반

Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning

2019-07-09 · Yu Zhang, Ron J. Weiss, Heiga Zen, Yonghui Wu 외

We present a multispeaker, multilingual text-to-speech (TTS) synthesis model based on Tacotron that is able to produce high quality speech in multiple languages. Moreover, the model is able to transfer voices across lang…

Speech Synthesistext-to-speechText to SpeechVoice Cloning

SpeakerStew: Scaling to Many Languages with a Triaged Multilingual Text-Dependent and Text-Independent Speaker Verification System

2021-04-05 · Roza Chojnacka, Jason Pelecanos, Quan Wang, Ignacio Lopez Moreno

In this paper, we describe SpeakerStew - a hybrid system to perform speaker verification on 46 languages. Two core ideas were explored in this system: (1) Pooling training data of different languages together for multili…

Speaker RecognitionSpeaker VerificationText-Independent Speaker Verification

Multilingual Reasoning Gym: Multilingual Scaling of Procedural Reasoning Environments

2026-03-11 · Konstantin Dobler, Simon Lehnerer, Federico Scozzafava, Jonathan Janke 외 arxiv

We present the Multilingual Reasoning Gym, an extension of Reasoning Gym (Stojanovski et al., 2025), that procedurally generates verifiable reasoning problems across 14 languages. We translate templates for 94 tasks with…

Reinforcement Learning

ERNIE-SAT: Speech and Text Joint Pretraining for Cross-Lingual Multi-Speaker Text-to-Speech

2022-11-07 · Xiaoran Fan, Chao Pang, Tian Yuan, He Bai 외

Speech representation learning has improved both speech understanding and speech synthesis tasks for single language. However, its ability in cross-lingual scenarios has not been explored. In this paper, we extend the pr…

Representation LearningSpeech Representation LearningSpeech Synthesistext-to-speech+3

SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speech

2022-06-24 · Hyunjae Cho, Wonbin Jung, Junhyeok Lee, Sang Hoon Woo

In this paper, we present SANE-TTS, a stable and natural end-to-end multilingual TTS model. By the difficulty of obtaining multilingual corpus for given speaker, training multilingual TTS model with monolingual corpora i…

Rhythmtext-to-speechText to Speech