Papers with Code 아카이브
Text to Speech
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 2
- 보존된 평가 기록
- 2
import gTTS import os def text_to_speech_kurdish(text, output_file="output.mp3"): # گۆڕینی نووسین بۆ دەنگ بە زمانی کوردی (هەڵبژاردنی زمانی "ku" بۆ کوردی) tts = gTTS(text=text, lang='ku', slow=False) tts.save(output_file) os.system(f"start {output_file}") # کردنەوەی فایلە دەنگییەکە (لە Windows) # نموونە: text_to_speech_kurdish("سڵاو، ئەمە دەنگی منە بە زمانی کوردی.")
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Impact of Frame Rates on Speech Tokenizer: A Case Study on Mandarin and English
OZSpeech: One-step Zero-shot Speech Synthesis with Learned-Prior-Conditioned Flow Matching
Shallow Flow Matching for Coarse-to-Fine Text-to-Speech Synthesis
BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset
Audio Turing Test: Benchmarking the Human-likeness of Large Language Model-based Text-to-Speech Systems in Chinese
UDDETTS: Unifying Discrete and Dimensional Emotions for Controllable Emotional Text-to-Speech
Lightweight End-to-end Text-to-speech Synthesis for low resource on-device applications
MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder
Bridging the Gap: An Intermediate Language for Enhanced and Cost-Effective Grapheme-to-Phoneme Conversion with Homographs with Multiple Pronunciations Disambiguation
Teochew-Wild: The First In-the-wild Teochew Dataset with Orthographic Annotations
FlexSpeech: Towards Stable, Controllable and Expressive Text-to-Speech
VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model
Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play
Generating Narrated Lecture Videos from Slides with Synchronized Highlights
Sadeed: Advancing Arabic Diacritization Through Small Language Model
Towards Flow-Matching-based TTS without Classifier-Free Guidance
ClonEval: An Open Voice Cloning Benchmark
A Multi-Agent Framework for Automated Qinqiang Opera Script Generation Using Large Language Models
EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting
GOAT-TTS: Expressive and Realistic Speech Generation via A Dual-Branch LLM
AutoStyle-TTS: Retrieval-Augmented Generation based Automatic Style Matching Text-to-Speech Synthesis
Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis
Generalized Multilingual Text-to-Speech Generation with Language-Aware Style Adaptation
SlimSpeech: Lightweight and Efficient Text-to-Speech with Slim Rectified Flow
Empowering Global Voices: A Data-Efficient, Phoneme-Tone Adaptive Approach to High-Fidelity Speech Synthesis
SpeakEasy: Enhancing Text-to-Speech Interactions for Expressive Content Creation
RWKVTTS: Yet another TTS based on RWKV-7
TeleAntiFraud-28k: An Audio-Text Slow-Thinking Dataset for Telecom Fraud Detection
Speculative End-Turn Detector for Efficient Speech Chatbot Assistant
SupertonicTTS: Towards Highly Scalable and Efficient Text-to-Speech System
DeepAudio-V1:Towards Multi-Modal Multi-Stage End-to-End Video to Speech and Audio Generation
Dual Audio-Centric Modality Coupling for Talking Head Generation
Your voice is your voice: Supporting Self-expression through Speech Generation and LLMs in Augmented and Alternative Communication
MoonCast: High-Quality Zero-Shot Podcast Generation
MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.