Speech

음성 기술은 컴퓨터 시스템이 인간의 음성을 처리하여 음성 인식, 합성, 및 이해를 달성하는 능력을 말합니다. 이 기술의 목표는 사용자 경험을 향상시키며 효율적으로 상호작용할 수 있는 지능형 시스템을 구축하는 것입니다. 음성 기술은 가상 비서, 고객 서비스 시스템, 음성 번역 등 다양한 분야에서 널리 적용되어, 인간과 컴퓨터 간의 상호작용을 더욱 자연스럽고 편리하게 만드는 데 크게 기여하고 있습니다.

Speech Dereverberation

6개 논문 | 5개 벤치마크

Spoken language identification

Speech

Speech Dereverberation

Spoken language identification

Speech Separation

Speech Extraction

Bandwidth Extension

Spoken Language Understanding

Audio-Visual Speech Recognition

Voice Conversion

Cultural Vocal Bursts Intensity Prediction

Dialogue Generation

Speech Enhancement

Keyword Spotting

Speaker Identification

Speech Synthesis

Distant Speech Recognition

Acoustic Unit Discovery

Vocal Bursts Type Prediction

Speech Recognition

Speaker Verification

Speaker Recognition

Accented Speech Recognition

Text-To-Speech Synthesis

Story Generation

Visual Speech Recognition

Multimodal Emotion Recognition

Lip to Speech Synthesis

Noisy Speech Recognition

Speech Denoising

Arabic Text Diacritization

Speaker Diarization

Automatic Lyrics Transcription

Speech-to-Speech Translation

Audio Deepfake Detection

Spoken Command Recognition

Phone-level pronunciation scoring

Automatic Phoneme Recognition

Automatic Speech Recognition (ASR)

Speech Emotion Recognition

Word-level pronunciation scoring

A-VB High

Utterance-level pronounciation scoring

Voice Query Recognition

A-VB Culture

A-VB Two

Speech Synthesis - Gujarati

Speech Synthesis - Assamese

Speech Synthesis - Bengali

Speech Synthesis - Bodo

Speech Synthesis - Hindi

Speech Synthesis - Kannada

Speech Synthesis - Malayalam

Speech Synthesis - Manipuri

Speech Synthesis - Marathi

Speech Synthesis - Rajasthani

Speech Synthesis - Tamil

Speech Synthesis - Telugu