HyperAI
AccueilActualitésArticles de recherche récentsTutorielsEnsembles de donnéesWikiSOTAModèles LLMClassement GPUÉvénements
Recherche
À propos
HyperAI

Speech

La technologie de la parole concerne la capacité des systèmes informatiques à traiter le langage parlé humain, visant à réaliser la reconnaissance vocale, la synthèse et la compréhension de la parole. Son objectif est de créer des systèmes intelligents capables d'interagir efficacement, améliorant ainsi l'expérience utilisateur. Elle est largement utilisée dans les assistants virtuels, les systèmes de service client, la traduction vocale et d'autres domaines, contribuant de manière significative à la naturalité et à la facilité de l'interaction homme-machine.

Speech Dereverberation

6 articles | 5 benchmarks

Spoken language identification

6 articles | 12 benchmarks

Speech Separation

46 articles | 19 benchmarks

Speech Extraction

1 articles | 1 benchmarks

Bandwidth Extension

2 articles | 6 benchmarks

Spoken Language Understanding

20 articles | 5 benchmarks

Audio-Visual Speech Recognition

19 articles | 4 benchmarks

Voice Conversion

3 articles | 3 benchmarks

Cultural Vocal Bursts Intensity Prediction

2 articles | 1 benchmarks

Dialogue Generation

12 articles | 13 benchmarks

Speech Enhancement

63 articles | 14 benchmarks

Keyword Spotting

53 articles | 10 benchmarks

Speaker Identification

9 articles | 4 benchmarks

Speech Synthesis

19 articles | 5 benchmarks

Distant Speech Recognition

4 articles | 2 benchmarks

Acoustic Unit Discovery

1 articles | 1 benchmarks

Vocal Bursts Type Prediction

1 articles | 1 benchmarks

Speech Recognition

135 articles | 148 benchmarks

Speaker Verification

12 articles | 12 benchmarks

Speaker Recognition

2 articles | 1 benchmarks

Accented Speech Recognition

2 articles | 4 benchmarks

Text-To-Speech Synthesis

14 articles | 6 benchmarks

Story Generation

2 articles | 5 benchmarks

Visual Speech Recognition

2 articles | 2 benchmarks

Multimodal Emotion Recognition

12 articles | 7 benchmarks

Lip to Speech Synthesis

1 articles | 1 benchmarks

Noisy Speech Recognition

4 articles | 2 benchmarks

Speech Denoising

1 articles | 2 benchmarks

Arabic Text Diacritization

7 articles | 2 benchmarks

Speaker Diarization

10 articles | 15 benchmarks

Automatic Lyrics Transcription

2 articles | 5 benchmarks

Speech-to-Speech Translation

5 articles | 3 benchmarks

Audio Deepfake Detection

8 articles | 1 benchmarks

Spoken Command Recognition

3 articles | 1 benchmarks

Phone-level pronunciation scoring

6 articles | 1 benchmarks

Automatic Phoneme Recognition

1 articles | 6 benchmarks

Automatic Speech Recognition (ASR)

11 articles | 8 benchmarks

Speech Emotion Recognition

31 articles | 15 benchmarks

Word-level pronunciation scoring

3 articles | 1 benchmarks

A-VB High

1 articles | 1 benchmarks

Utterance-level pronounciation scoring

3 articles | 1 benchmarks

Voice Query Recognition

1 articles | 1 benchmarks

A-VB Culture

1 articles | 1 benchmarks

A-VB Two

1 articles | 1 benchmarks

Speech Synthesis - Gujarati

2 articles | 2 benchmarks

Speech Synthesis - Assamese

1 articles | 1 benchmarks

Speech Synthesis - Bengali

1 articles | 1 benchmarks

Speech Synthesis - Bodo

1 articles | 1 benchmarks

Speech Synthesis - Hindi

1 articles | 1 benchmarks

Speech Synthesis - Kannada

1 articles | 1 benchmarks

Speech Synthesis - Malayalam

1 articles | 1 benchmarks

Speech Synthesis - Manipuri

1 articles | 1 benchmarks

Speech Synthesis - Marathi

1 articles | 1 benchmarks

Speech Synthesis - Rajasthani

1 articles | 1 benchmarks

Speech Synthesis - Tamil

1 articles | 1 benchmarks

Speech Synthesis - Telugu

1 articles | 1 benchmarks