Zero-Shot Audio Classification Via Semantic Embeddings

Research output: Contribution to journalArticleScientificpeer-review


In this paper, we study zero-shot learning in audio classification via semantic embeddings extracted from textual labels and sentence descriptions of sound classes. Our goal is to obtain a classifier that is capable of recognizing audio instances of sound classes that have no available training samples, but only semantic side information. We employ a bilinear compatibility framework to learn an acoustic-semantic projection between intermediate-level representations of audio instances and sound classes, i.e., acoustic embeddings and semantic embeddings. We use VGGish to extract deep acoustic embeddings from audio clips, and pre-trained language models (Word2Vec, GloVe, BERT) to generate either label embeddings from textual labels or sentence embeddings from sentence descriptions of sound classes. Audio classification is performed by a linear compatibility function that measures how compatible an acoustic embedding and a semantic embedding are. We evaluate the proposed method on a small balanced dataset ESC-50 and a large-scale unbalanced audio subset of AudioSet. The experimental results show that classification performance is significantly improved by involving sound classes that are semantically close to the test classes in training. Meanwhile, we demonstrate that both label embeddings and sentence embeddings are useful for zero-shot learning. Classification performance is improved by concatenating label/sentence embeddings generated with different language models. With their hybrid concatenations, the results are improved further.

Original languageEnglish
Pages (from-to)1233-1242
Number of pages10
JournalIEEE/ACM Transactions on Audio Speech and Language Processing
Publication statusPublished - 2021
Publication typeA1 Journal article-refereed


  • Audio classification
  • semantic embedding
  • zero-shot learning

Publication forum classification

  • Publication forum level 3

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Acoustics and Ultrasonics
  • Computational Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Zero-Shot Audio Classification Via Semantic Embeddings'. Together they form a unique fingerprint.

Cite this