AIbase
EN
Home
Trillsson3 Ft Keyword Spotting 13
T

Trillsson3 Ft Keyword Spotting 13

Developed by vumichien
Audio classification model based on TRillsson3 architecture, fine-tuned on the superb dataset for keyword spotting tasks
Audio Classification
Transformers
#Voice keyword detection#High-accuracy audio classification#Non-semantic speech features
Downloads 32
Release Time : 10/23/2022

Model Overview

This model is a fine-tuned version of vumichien/nonsemantic-speech-trillsson3 on the superb dataset, specifically designed for keyword spotting tasks, achieving 91.53% accuracy on the evaluation set.

Model Features

High accuracy
Achieves 91.53% accuracy on the superb dataset's evaluation set
Based on TRillsson3 architecture
Fine-tuned using advanced non-semantic speech representation architecture
Efficient training
Optimized training with Adam optimizer and linear learning rate scheduler

Model Capabilities

Audio classification
Keyword spotting
Speech feature extraction

Use Cases

Voice interaction
Smart device wake word detection
Used to detect specific wake words in smart devices
91.53% recognition accuracy
Speech analysis
Voice command recognition
Recognize specific commands or keywords in speech
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
EnglishįŽ€äŊ“中文įšéĢ”中文ãĢãģんご
Š 2025AIbase