Junyi Ao

ajyy's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 8 papers 1 day ago

Solla: Towards a Speech-Oriented LLM That Hears Acoustic Context

Paper • 2503.15338 • Published Mar 19, 2025

Overview of the Amphion Toolkit (v0.2)

Paper • 2501.15442 • Published Jan 26, 2025 • 4

What Did I Just Say? Self-Listening for Full-Duplex Speech Models

Paper • 2609.05592 • Published 21 days ago • 25

SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words

Paper • 2406.13340 • Published Jun 19, 2024

Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data

Paper • 2203.17113 • Published Mar 31, 2022

LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT

Paper • 2203.15610 • Published Mar 29, 2022

SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing

Paper • 2110.07205 • Published Oct 14, 2021 • 6

EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Models

Paper • 2510.22758 • Published Oct 26, 2025 • 1

upvoted a paper 15 days ago

What Did I Just Say? Self-Listening for Full-Duplex Speech Models

Paper • 2609.05592 • Published 21 days ago • 25

liked a model over 1 year ago

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

Text Generation • 33B • Updated Feb 24, 2025 • 476k • • 1.62k

liked 2 models over 2 years ago

NousResearch/Meta-Llama-3-8B-Instruct

Text Generation • 8B • Updated Jul 23, 2024 • 85k • • 103

openai/whisper-large-v3

Automatic Speech Recognition • 2B • Updated Aug 12, 2024 • 4.7M • • 6.37k

liked 2 datasets over 2 years ago

facebook/multilingual_librispeech

Viewer • Updated Aug 12, 2024 • 1.49M • 39k • 191

legacy-datasets/multilingual_librispeech

Updated Sep 10, 2024 • 182 • 17

liked a model over 2 years ago

meta-llama/Llama-2-7b-chat-hf

Text Generation • 7B • Updated Apr 17, 2024 • 504k • 4.88k

liked 2 datasets over 2 years ago

timit-asr/timit_asr

Updated Sep 10, 2024 • 235 • 27

google/fleurs

Viewer • Updated May 15 • 768k • 101k • 468

upvoted a paper over 2 years ago

SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing

Paper • 2110.07205 • Published Oct 14, 2021 • 6

upvoted a collection over 2 years ago

SpeechT5

Collection

The SpeechT5 framework consists of a shared seq2seq and six modal-specific (speech/text) pre/post-nets that can address a few audio-related tasks. • 8 items • Updated May 1, 2025 • 28

liked a model over 2 years ago

reazon-research/reazonspeech-nemo-v2

Automatic Speech Recognition • Updated Feb 13, 2024 • 1.6k • 39