Speech

385 benchmarks 147 tasks 583 datasets 8,048 papers with code archive 2025-07-28

Syntology code harvested from 1,784 of the papers with code counted above at least one sample ran for 1,382 of them per-sample status is on each paper page

Benchmarks are leaderboard tables with at least one row whose task is in this area, counted by the task's area and not by the archive's per-table category tag, which tags 409 tables with Speech; datasets are those the archive tags with a task in this area; papers with code are catalogue papers tagged with a task in this area that list at least one repository. Task images are not shown (the archive's image host no longer serves them).

Parent tasks

21 tasks in Speech have sub-tasks in the archive's task tree, most benchmarks first, then most papers with code. Each section shows up to 5 sub-tasks; the task page lists them all.

Speech Recognition (11)
Text Generation (25)
Speech Separation (1)
Speech Enhancement (4)
Speech Emotion Recognition (4)
Speaker Verification (3)
Keyword Spotting (2)
Automatic Speech Recognition (ASR) (1)
Emotion Recognition (12)
DeepFake Detection (5)
Text-To-Speech Synthesis (2)
Speech Synthesis (15)
Spoken Language Understanding (2)
Audio-Visual Speech Recognition (1)
Audio Generation (4)
Visual Speech Recognition (1)
Chatbot (1)
1 Image, 2*2 Stitchi (12)
Dialogue (21)
Speaker Separation (1)
Pronunciation Assessment (3)

Speech Recognition

65 benchmarks · 1,373 papers with code

Automatic Speech Recognition (ASR)

9 benchmarks · 622 papers with code

Automatic Lyrics Transcription

5 benchmarks · 9 papers with code

Accented Speech Recognition

4 benchmarks · 6 papers with code

Visual Speech Recognition

2 benchmarks · 62 papers with code

Distant Speech Recognition

2 benchmarks · 10 papers with code

5 shown of 11 sub-tasks (1 filed under another area). All sub-tasks of Speech Recognition →

Text Generation

20 benchmarks · 2,047 papers with code

Data-to-Text Generation

26 benchmarks · 112 papers with code

Dialogue Generation

13 benchmarks · 265 papers with code

Table-to-Text Generation

8 benchmarks · 43 papers with code

Code Documentation Generation

7 benchmarks · 7 papers with code

Multi-Document Summarization

5 benchmarks · 113 papers with code

5 shown of 25 sub-tasks (10 filed under another area). All sub-tasks of Text Generation →

Speech Separation

19 benchmarks · 120 papers with code

Speech Extraction

1 benchmark · 10 papers with code

1 shown of 1 sub-task.

Speech Enhancement

17 benchmarks · 280 papers with code

Bandwidth Extension

6 benchmarks · 18 papers with code

Speech Dereverberation

5 benchmarks · 20 papers with code

Packet Loss Concealment

0 benchmarks · 4 papers with code

Speech Intelligibility Evaluation

0 benchmarks · 0 papers with code

4 shown of 4 sub-tasks.

Speech Emotion Recognition

16 benchmarks · 139 papers with code

Vocal Bursts Intensity Prediction

1 benchmark · 775 papers with code

Vocal Bursts Valence Prediction

1 benchmark · 265 papers with code

Vocal Bursts Type Prediction

1 benchmark · 155 papers with code

Cultural Vocal Bursts Intensity Prediction

1 benchmark · 93 papers with code

4 shown of 4 sub-tasks.

Speaker Verification

12 benchmarks · 200 papers with code

Audio Deepfake Detection

2 benchmarks · 35 papers with code

Text-Independent Speaker Verification

0 benchmarks · 19 papers with code

Text-Dependent Speaker Verification

0 benchmarks · 2 papers with code

3 shown of 3 sub-tasks.

Keyword Spotting

10 benchmarks · 113 papers with code

Visual Keyword Spotting

3 benchmarks · 4 papers with code

Small-Footprint Keyword Spotting

0 benchmarks · 9 papers with code

2 shown of 2 sub-tasks.

Automatic Speech Recognition (ASR)

9 benchmarks · 622 papers with code

Automatic Phoneme Recognition

6 benchmarks · 1 paper with code

1 shown of 1 sub-task.

Emotion Recognition

9 benchmarks · 614 papers with code

Speech Emotion Recognition

16 benchmarks · 139 papers with code

Emotion Recognition in Conversation

16 benchmarks · 83 papers with code

Multimodal Emotion Recognition

7 benchmarks · 80 papers with code

Emotion Recognition in Context

4 benchmarks · 5 papers with code

EEG Emotion Recognition

3 benchmarks · 14 papers with code

5 shown of 12 sub-tasks (1 filed under another area). All sub-tasks of Emotion Recognition →

DeepFake Detection

8 benchmarks · 237 papers with code

Audio Deepfake Detection

2 benchmarks · 35 papers with code

Multimodal Forgery Detection

1 benchmark · 1 paper with code

Synthetic Speech Detection

0 benchmarks · 12 papers with code

diffusion-generated faces detection

0 benchmarks · 1 paper with code

Human Detection of Deepfakes

0 benchmarks · 1 paper with code

5 shown of 5 sub-tasks.

Text-To-Speech Synthesis

6 benchmarks · 104 papers with code

Prosody Prediction

1 benchmark · 4 papers with code

Zero-Shot Multi-Speaker TTS

0 benchmarks · 3 papers with code

2 shown of 2 sub-tasks.

Speech Synthesis

5 benchmarks · 366 papers with code

Speech Synthesis - Gujarati

2 benchmarks · 2 papers with code

Speech Synthesis - Assamese

1 benchmark · 1 paper with code

Speech Synthesis - Bengali

1 benchmark · 1 paper with code

Speech Synthesis - Bodo

1 benchmark · 1 paper with code

Speech Synthesis - Hindi

1 benchmark · 1 paper with code

5 shown of 15 sub-tasks. All sub-tasks of Speech Synthesis →

Spoken Language Understanding

5 benchmarks · 135 papers with code

Spoken language identification

12 benchmarks · 13 papers with code

Speech Tokenization

0 benchmarks · 9 papers with code

2 shown of 2 sub-tasks.

Audio-Visual Speech Recognition

4 benchmarks · 42 papers with code

Text to Speech

2 benchmarks · 399 papers with code

1 shown of 1 sub-task.

Audio Generation

3 benchmarks · 124 papers with code

Audio Super-Resolution

4 benchmarks · 16 papers with code

Video-to-Sound Generation

1 benchmark · 6 papers with code

Voice Cloning

0 benchmarks · 36 papers with code

Room Impulse Response (RIR)

0 benchmarks · 18 papers with code

4 shown of 4 sub-tasks (1 filed under another area).

Visual Speech Recognition

2 benchmarks · 62 papers with code

Lip to Speech Synthesis

1 benchmark · 6 papers with code

1 shown of 1 sub-task (1 filed under another area).

Chatbot

1 benchmark · 269 papers with code

Dialogue Generation

13 benchmarks · 265 papers with code

1 shown of 1 sub-task (1 filed under another area).

1 Image, 2*2 Stitchi

1 benchmark · 3 papers with code

Pose Estimation

31 benchmarks · 1,679 papers with code

Text-to-Image Generation

17 benchmarks · 546 papers with code

Image Deblurring

9 benchmarks · 167 papers with code

Virtual Try-on

9 benchmarks · 114 papers with code

Style Transfer

3 benchmarks · 759 papers with code

5 shown of 12 sub-tasks (9 filed under another area). All sub-tasks of 1 Image, 2*2 Stitchi →

Dialogue

1 benchmark · 1 paper with code

Dialogue Generation

13 benchmarks · 265 papers with code

Visual Dialog

8 benchmarks · 56 papers with code

Dialogue State Tracking

7 benchmarks · 138 papers with code

Dialogue Act Classification

5 benchmarks · 23 papers with code

Task-Oriented Dialogue Systems

4 benchmarks · 131 papers with code

5 shown of 21 sub-tasks (6 filed under another area). All sub-tasks of Dialogue →

Speaker Separation

0 benchmarks · 13 papers with code

Multi-Speaker Source Separation

0 benchmarks · 6 papers with code

1 shown of 1 sub-task.

Pronunciation Assessment

0 benchmarks · 0 papers with code

Phone-level pronunciation scoring

1 benchmark · 5 papers with code

Utterance-level pronounciation scoring

1 benchmark · 2 papers with code

Word-level pronunciation scoring

1 benchmark · 2 papers with code

3 shown of 3 sub-tasks.

Tasks with no parent task

27 tasks in Speech sit at the top of the archive's task tree with no sub-tasks of their own, most benchmarks first, then most papers with code.

Task tree and counts are the archive's, frozen 2025-07-28 archive 2025-07-28. Nothing here is re-ranked.