tsaoni/dynamic-superb-hw

git repo modified from dynamic-superb

stars

commits

Python

primary language

Nov 28, 2023

updated

README

bash main.sh

you can change settings in main.py

EnvironmentalSoundClassification_ESC50-Animals	SpeechTextMatching_LJSpeech	NoiseSNRLevelPrediction_VCTK_MUSAN-Gaussian	SpoofDetection_ASVspoof2017	DialogueActClassification_DailyTalk	SpeakerCounting_LibriTTS-TestClean
4.000%	96.650%	33.700%	20.700%	60.750%	41.650%

note. the original repo are here

15 commits

Panda-Lorrain/xh-202615-robust-asr

XH-202615 复杂交互场景的抗干扰语音指令识别技术 - Target-Speaker ASR + 意图拒识方案

BUTSpeechFIT/TS-ASR-Whisper

122

monishmal3375/nova-vad

Lightweight, explainable VAD that beats Silero and WebRTC on noisy audio. No GPU required.

microsoft/DNS-Challenge

This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS)…

1,465

BUTSpeechFIT/SOT-DiCoW

Multi-talker ASR based on DiCoW with Serialized Output Training

Cicada-33-01/MTP-Codebase

YuanGongND/whisper-at

Code and Pretrained Models for Interspeech 2023 Paper "Whisper-AT: Noise-Robust Automatic Speech…

426

nickjw0205/Improving-ASR-with-LLM-Description

Python

69.8%

Shell

25.6%

Perl

3.1%

README

bash main.sh

you can change settings in main.py

EnvironmentalSoundClassification_ESC50-Animals	SpeechTextMatching_LJSpeech	NoiseSNRLevelPrediction_VCTK_MUSAN-Gaussian	SpoofDetection_ASVspoof2017	DialogueActClassification_DailyTalk	SpeakerCounting_LibriTTS-TestClean
4.000%	96.650%	33.700%	20.700%	60.750%	41.650%

note. the original repo are here