HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Speech

Speech technology refers to the capability of computer systems to process human speech, aiming to achieve speech recognition, synthesis, and understanding. Its goal is to build intelligent systems that can interact efficiently, enhancing user experience. It is widely applied in virtual assistants, customer service systems, voice translation, and other fields, significantly promoting the naturalness and convenience of human-computer interaction.

Speech Recognition

135 papers | 148 benchmarks

Speech Separation

46 papers | 19 benchmarks

Speaker Diarization

10 papers | 15 benchmarks

Speech Emotion Recognition

31 papers | 15 benchmarks

Speech Enhancement

63 papers | 14 benchmarks

Dialogue Generation

12 papers | 13 benchmarks

Spoken language identification

6 papers | 12 benchmarks

Speaker Verification

12 papers | 12 benchmarks

Keyword Spotting

53 papers | 10 benchmarks

Automatic Speech Recognition (ASR)

11 papers | 8 benchmarks

Multimodal Emotion Recognition

12 papers | 7 benchmarks

Bandwidth Extension

2 papers | 6 benchmarks

Text-To-Speech Synthesis

14 papers | 6 benchmarks

Automatic Phoneme Recognition

1 papers | 6 benchmarks

Speech Dereverberation

6 papers | 5 benchmarks

Spoken Language Understanding

20 papers | 5 benchmarks

Speech Synthesis

19 papers | 5 benchmarks

Story Generation

2 papers | 5 benchmarks

Automatic Lyrics Transcription

2 papers | 5 benchmarks

Audio-Visual Speech Recognition

19 papers | 4 benchmarks

Speaker Identification

9 papers | 4 benchmarks

Accented Speech Recognition

2 papers | 4 benchmarks

Voice Conversion

3 papers | 3 benchmarks

Speech-to-Speech Translation

5 papers | 3 benchmarks

Distant Speech Recognition

4 papers | 2 benchmarks

Visual Speech Recognition

2 papers | 2 benchmarks

Noisy Speech Recognition

4 papers | 2 benchmarks

Speech Denoising

1 papers | 2 benchmarks

Arabic Text Diacritization

7 papers | 2 benchmarks

Speech Synthesis - Gujarati

2 papers | 2 benchmarks

Speech Extraction

1 papers | 1 benchmarks

Cultural Vocal Bursts Intensity Prediction

2 papers | 1 benchmarks

Acoustic Unit Discovery

1 papers | 1 benchmarks

Vocal Bursts Type Prediction

1 papers | 1 benchmarks

Speaker Recognition

2 papers | 1 benchmarks

Lip to Speech Synthesis

1 papers | 1 benchmarks

Audio Deepfake Detection

8 papers | 1 benchmarks

Spoken Command Recognition

3 papers | 1 benchmarks

Phone-level pronunciation scoring

6 papers | 1 benchmarks

Word-level pronunciation scoring

3 papers | 1 benchmarks

A-VB High

1 papers | 1 benchmarks

Utterance-level pronounciation scoring

3 papers | 1 benchmarks

Voice Query Recognition

1 papers | 1 benchmarks

A-VB Culture

1 papers | 1 benchmarks

A-VB Two

1 papers | 1 benchmarks

Speech Synthesis - Assamese

1 papers | 1 benchmarks

Speech Synthesis - Bengali

1 papers | 1 benchmarks

Speech Synthesis - Bodo

1 papers | 1 benchmarks

Speech Synthesis - Hindi

1 papers | 1 benchmarks

Speech Synthesis - Kannada

1 papers | 1 benchmarks

Speech Synthesis - Malayalam

1 papers | 1 benchmarks

Speech Synthesis - Manipuri

1 papers | 1 benchmarks

Speech Synthesis - Marathi

1 papers | 1 benchmarks

Speech Synthesis - Rajasthani

1 papers | 1 benchmarks

Speech Synthesis - Tamil

1 papers | 1 benchmarks

Speech Synthesis - Telugu

1 papers | 1 benchmarks