Audio Retrieval Based on Milvus

Audio retrieval with Milvus makes it possible to classify and analyze sound data in real-time.

Processing Technologies

Audio feature extraction

Vector similarity search

System overview

Audio retrieval system powered by Milvus.
Audio retrieval system powered by Milvus.

Step 1: Insert data

wav_name, vectors_audio = get_audio_embedding(audio_path)
if vectors_audio:  
     embeddings.append(vectors_audio)  
     wav_names.append(wav_name)   ids_milvus = insert_vectors(milvus_client, table_name, embeddings) 
get_ids_correlation(ids_milvus, wav_name)   
load_data_to_mysql(conn, cursor, table_name) 

Step 2: Audio search

_, vectors_audio = get_audio_embedding(audio_filename)   results = search_vectors(milvus_client, table_name, [vectors_audio], METRIC_TYPE, TOP_K)   
ids_milvus = [x.id for x in results[0]]  
audio_name = search_by_milvus_ids(conn, cursor, ids_milvus, table_name)  

API reference and demo

API

Demo

Audio search demo powered by Milvus.
Audio search demo powered by Milvus.

Conclusion

References

Don’t be a stranger

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Milvus

Open-source Vector Database Powering AI Applications. #SimilaritySearch #Embeddings #MachineLearning